[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-ded8c9ac1faa0341-vibevoice-efficient-long-form-voice-ai-models-summary":3,"summaries-facets-categories":113,"summary-related-ded8c9ac1faa0341-vibevoice-efficient-long-form-voice-ai-models-summary":3683},{"id":4,"title":5,"ai":6,"body":13,"categories":63,"created_at":64,"date_modified":64,"description":56,"extension":65,"faq":64,"featured":66,"kicker_label":64,"meta":67,"navigation":96,"path":97,"published_at":64,"question":64,"scraped_at":98,"seo":99,"sitemap":100,"source_id":101,"source_name":102,"source_type":103,"source_url":104,"stem":105,"tags":106,"thumbnail_url":64,"tldr":110,"tweet":64,"unknown_tags":111,"__hash__":112},"summaries\u002Fsummaries\u002Fded8c9ac1faa0341-vibevoice-efficient-long-form-voice-ai-models-summary.md","VibeVoice: Efficient Long-Form Voice AI Models",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",9625,2144,20668,0.00297435,{"type":14,"value":15,"toc":55},"minimark",[16,21,25,28,32,35,38,42,45,48,52],[17,18,20],"h2",{"id":19},"efficient-tokenization-drives-long-form-processing","Efficient Tokenization Drives Long-Form Processing",[22,23,24],"p",{},"VibeVoice models process extended audio via acoustic and semantic tokenizers at 7.5Hz frame rate, preserving fidelity while handling sequences up to 64K tokens. This enables single-pass transcription of 60-minute audio or synthesis of 90-minute speech without chunking losses. A next-token diffusion framework combines an LLM for textual context\u002Fdialogue flow with a diffusion head for high-fidelity acoustics, outperforming chunked baselines on diarization error rate (DER), concatenated-padded word error rate (cpWER), and timestamped cpWER (tcpWER) per benchmarks.",[22,26,27],{},"Apply this by loading models from Hugging Face (e.g., microsoft\u002FVibeVoice-ASR-7B, VibeVoice-1.5B, VibeVoice-Realtime-0.5B) for inference; vLLM plugin accelerates ASR serving.",[17,29,31],{"id":30},"asr-delivers-structured-60-minute-transcriptions","ASR Delivers Structured 60-Minute Transcriptions",[22,33,34],{},"VibeVoice-ASR-7B transcribes long-form audio with joint ASR, speaker diarization (Who), timestamps (When), and content (What). Provide customized hotwords (names\u002Fterms\u002Fcontext) to boost accuracy on domain-specific audio. Natively supports 50+ languages in one pass, avoiding context loss from short-segment processing. Finetuning scripts available; integrated into Hugging Face Transformers v5.3.0. Test via playground (aka.ms\u002Fvibevoice-asr) or Colab.",[22,36,37],{},"Outcomes: Consistent speaker tracking and semantic coherence over full hour, with community apps like Vibing using it for voice input on macOS\u002FWindows.",[17,39,41],{"id":40},"tts-enables-expressive-multi-speaker-dialogues","TTS Enables Expressive Multi-Speaker Dialogues",[22,43,44],{},"VibeVoice-TTS-1.5B generates up to 90 minutes of speech with 4 distinct speakers, natural turn-taking, and emotional nuances in English\u002FChinese\u002Fcross-lingual. Handles spontaneous singing and long conversations (e.g., 45min 4-person climate discussion). VibeVoice-Realtime-0.5B adds streaming text input, ~300ms first audible latency, and 10-minute robust generation for deployment. Note: TTS code removed September 2025 due to misuse beyond research intent; use HF weights. Experimental voices cover 9 languages + 11 English styles. Try Realtime on Colab.",[22,46,47],{},"ICLR 2026 Oral acceptance validates long-form\u002Fmulti-speaker quality.",[17,49,51],{"id":50},"quick-starts-and-extensions","Quick Starts and Extensions",[22,53,54],{},"Stream TTS via Colab notebook; ASR playground for instant testing. Finetune ASR with provided code. Contribute per CONTRIBUTING.md; MIT license. Track 39.1k stars, 4.5k forks.",{"title":56,"searchDepth":57,"depth":57,"links":58},"",2,[59,60,61,62],{"id":19,"depth":57,"text":20},{"id":30,"depth":57,"text":31},{"id":40,"depth":57,"text":41},{"id":50,"depth":57,"text":51},[],null,"md",false,{"content_references":68,"triage":91},[69,74,77,80,85,87],{"type":70,"title":71,"url":72,"context":73},"paper","VibeVoice-TTS Technique Report","https:\u002F\u002Fopenreview.net\u002Fpdf?id=FihSkzyxdv","cited",{"type":70,"title":75,"url":76,"context":73},"VibeVoice-ASR Technique Report","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2601.18184",{"type":70,"title":78,"url":79,"context":73},"Next-Token Diffusion","https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.08635",{"type":81,"title":82,"url":83,"context":84},"tool","Hugging Face Transformers","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftransformers\u002Freleases\u002Ftag\u002Fv5.3.0","mentioned",{"type":81,"title":86,"context":84},"vLLM",{"type":88,"title":89,"url":90,"context":84},"other","Vibing Voice Input App","https:\u002F\u002Fgithub.com\u002FVibingJustSpeakIt\u002FVibing",{"relevance":92,"novelty":93,"quality":93,"actionability":93,"composite":94,"reasoning":95},5,4,4.35,"Category: AI & LLMs. The article provides in-depth information about the VibeVoice models, detailing their capabilities in long-form voice processing, which directly addresses the needs of developers looking to integrate advanced AI features into their products. It includes practical guidance on loading models and fine-tuning, making it actionable for the target audience.",true,"\u002Fsummaries\u002Fded8c9ac1faa0341-vibevoice-efficient-long-form-voice-ai-models-summary","2026-04-14 14:33:41",{"title":5,"description":56},{"loc":97},"ded8c9ac1faa0341","__oneoff__","article","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FVibeVoice","summaries\u002Fded8c9ac1faa0341-vibevoice-efficient-long-form-voice-ai-models-summary",[107,108,109],"ai-tools","open-source","llm","Microsoft's open-source VibeVoice uses 7.5Hz continuous tokenizers and next-token diffusion to enable single-pass 60min ASR with diarization\u002Ftimestamps\u002Fhotwords and 90min multi-speaker TTS, plus 300ms-latency realtime 0.5B model.",[],"p146Sf-23CBfMlhtLl7eAXLfBT958tTd9OjJaprDEy8",[114,117,120,123,126,129,131,133,135,137,139,141,144,146,148,150,152,154,156,158,160,162,165,168,170,172,175,177,179,182,184,186,188,190,192,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222,224,226,228,230,232,234,236,238,240,242,244,246,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681],{"categories":115},[116],"Developer Productivity",{"categories":118},[119],"Business & SaaS",{"categories":121},[122],"AI & LLMs",{"categories":124},[125],"AI Automation",{"categories":127},[128],"Product Strategy",{"categories":130},[122],{"categories":132},[116],{"categories":134},[119],{"categories":136},[],{"categories":138},[122],{"categories":140},[],{"categories":142},[143],"AI News & Trends",{"categories":145},[125],{"categories":147},[143],{"categories":149},[125],{"categories":151},[125],{"categories":153},[122],{"categories":155},[122],{"categories":157},[143],{"categories":159},[122],{"categories":161},[],{"categories":163},[164],"Design & Frontend",{"categories":166},[167],"Data Science & Visualization",{"categories":169},[143],{"categories":171},[],{"categories":173},[174],"Software Engineering",{"categories":176},[122],{"categories":178},[125],{"categories":180},[181],"Marketing & Growth",{"categories":183},[122],{"categories":185},[125],{"categories":187},[],{"categories":189},[],{"categories":191},[164],{"categories":193},[125],{"categories":195},[116],{"categories":197},[164],{"categories":199},[122],{"categories":201},[125],{"categories":203},[143],{"categories":205},[],{"categories":207},[],{"categories":209},[125],{"categories":211},[174],{"categories":213},[],{"categories":215},[119],{"categories":217},[],{"categories":219},[],{"categories":221},[125],{"categories":223},[125],{"categories":225},[122],{"categories":227},[],{"categories":229},[174],{"categories":231},[],{"categories":233},[],{"categories":235},[],{"categories":237},[122],{"categories":239},[181],{"categories":241},[164],{"categories":243},[164],{"categories":245},[122],{"categories":247},[125],{"categories":249},[122],{"categories":251},[122],{"categories":253},[125],{"categories":255},[125],{"categories":257},[167],{"categories":259},[143],{"categories":261},[125],{"categories":263},[181],{"categories":265},[125],{"categories":267},[128],{"categories":269},[],{"categories":271},[125],{"categories":273},[],{"categories":275},[125],{"categories":277},[174],{"categories":279},[164],{"categories":281},[122],{"categories":283},[],{"categories":285},[],{"categories":287},[125],{"categories":289},[],{"categories":291},[122],{"categories":293},[],{"categories":295},[116],{"categories":297},[174],{"categories":299},[119],{"categories":301},[143],{"categories":303},[122],{"categories":305},[],{"categories":307},[122],{"categories":309},[],{"categories":311},[174],{"categories":313},[167],{"categories":315},[],{"categories":317},[122],{"categories":319},[164],{"categories":321},[],{"categories":323},[164],{"categories":325},[125],{"categories":327},[],{"categories":329},[125],{"categories":331},[143],{"categories":333},[122],{"categories":335},[],{"categories":337},[125],{"categories":339},[122],{"categories":341},[128],{"categories":343},[],{"categories":345},[122],{"categories":347},[125],{"categories":349},[125],{"categories":351},[],{"categories":353},[167],{"categories":355},[122],{"categories":357},[],{"categories":359},[116],{"categories":361},[119],{"categories":363},[122],{"categories":365},[125],{"categories":367},[174],{"categories":369},[122],{"categories":371},[],{"categories":373},[],{"categories":375},[122],{"categories":377},[],{"categories":379},[164],{"categories":381},[],{"categories":383},[122],{"categories":385},[],{"categories":387},[125],{"categories":389},[122],{"categories":391},[164],{"categories":393},[],{"categories":395},[122],{"categories":397},[122],{"categories":399},[119],{"categories":401},[125],{"categories":403},[122],{"categories":405},[164],{"categories":407},[125],{"categories":409},[],{"categories":411},[],{"categories":413},[143],{"categories":415},[],{"categories":417},[122],{"categories":419},[119,181],{"categories":421},[],{"categories":423},[122],{"categories":425},[],{"categories":427},[],{"categories":429},[122],{"categories":431},[],{"categories":433},[122],{"categories":435},[436],"DevOps & Cloud",{"categories":438},[],{"categories":440},[143],{"categories":442},[164],{"categories":444},[],{"categories":446},[143],{"categories":448},[143],{"categories":450},[122],{"categories":452},[181],{"categories":454},[],{"categories":456},[119],{"categories":458},[],{"categories":460},[122,436],{"categories":462},[122],{"categories":464},[122],{"categories":466},[125],{"categories":468},[122,174],{"categories":470},[167],{"categories":472},[122],{"categories":474},[181],{"categories":476},[125],{"categories":478},[125],{"categories":480},[],{"categories":482},[125],{"categories":484},[122,119],{"categories":486},[],{"categories":488},[164],{"categories":490},[164],{"categories":492},[],{"categories":494},[],{"categories":496},[143],{"categories":498},[],{"categories":500},[116],{"categories":502},[174],{"categories":504},[122],{"categories":506},[164],{"categories":508},[125],{"categories":510},[174],{"categories":512},[143],{"categories":514},[164],{"categories":516},[],{"categories":518},[122],{"categories":520},[122],{"categories":522},[122],{"categories":524},[143],{"categories":526},[116],{"categories":528},[122],{"categories":530},[125],{"categories":532},[436],{"categories":534},[164],{"categories":536},[125],{"categories":538},[],{"categories":540},[],{"categories":542},[164],{"categories":544},[143],{"categories":546},[167],{"categories":548},[],{"categories":550},[122],{"categories":552},[122],{"categories":554},[119],{"categories":556},[122],{"categories":558},[122],{"categories":560},[143],{"categories":562},[],{"categories":564},[125],{"categories":566},[174],{"categories":568},[],{"categories":570},[122],{"categories":572},[122],{"categories":574},[125],{"categories":576},[],{"categories":578},[],{"categories":580},[122],{"categories":582},[],{"categories":584},[119],{"categories":586},[125],{"categories":588},[],{"categories":590},[116],{"categories":592},[122],{"categories":594},[119],{"categories":596},[143],{"categories":598},[],{"categories":600},[],{"categories":602},[],{"categories":604},[143],{"categories":606},[143],{"categories":608},[],{"categories":610},[],{"categories":612},[119],{"categories":614},[],{"categories":616},[],{"categories":618},[116],{"categories":620},[],{"categories":622},[181],{"categories":624},[125],{"categories":626},[119],{"categories":628},[125],{"categories":630},[],{"categories":632},[128],{"categories":634},[164],{"categories":636},[174],{"categories":638},[122],{"categories":640},[125],{"categories":642},[119],{"categories":644},[122],{"categories":646},[],{"categories":648},[],{"categories":650},[174],{"categories":652},[167],{"categories":654},[128],{"categories":656},[125],{"categories":658},[122],{"categories":660},[],{"categories":662},[436],{"categories":664},[],{"categories":666},[125],{"categories":668},[],{"categories":670},[],{"categories":672},[122],{"categories":674},[164],{"categories":676},[181],{"categories":678},[125],{"categories":680},[],{"categories":682},[116],{"categories":684},[],{"categories":686},[143],{"categories":688},[122,436],{"categories":690},[143],{"categories":692},[122],{"categories":694},[119],{"categories":696},[122],{"categories":698},[],{"categories":700},[119],{"categories":702},[],{"categories":704},[174],{"categories":706},[164],{"categories":708},[143],{"categories":710},[167],{"categories":712},[116],{"categories":714},[122],{"categories":716},[174],{"categories":718},[],{"categories":720},[],{"categories":722},[128],{"categories":724},[],{"categories":726},[122],{"categories":728},[],{"categories":730},[164],{"categories":732},[164],{"categories":734},[164],{"categories":736},[],{"categories":738},[],{"categories":740},[143],{"categories":742},[125],{"categories":744},[122],{"categories":746},[122],{"categories":748},[122],{"categories":750},[119],{"categories":752},[122],{"categories":754},[],{"categories":756},[174],{"categories":758},[174],{"categories":760},[119],{"categories":762},[],{"categories":764},[122],{"categories":766},[122],{"categories":768},[119],{"categories":770},[143],{"categories":772},[181],{"categories":774},[125],{"categories":776},[],{"categories":778},[164],{"categories":780},[],{"categories":782},[122],{"categories":784},[],{"categories":786},[119],{"categories":788},[125],{"categories":790},[],{"categories":792},[436],{"categories":794},[167],{"categories":796},[174],{"categories":798},[181],{"categories":800},[174],{"categories":802},[125],{"categories":804},[],{"categories":806},[],{"categories":808},[125],{"categories":810},[116],{"categories":812},[125],{"categories":814},[128],{"categories":816},[119],{"categories":818},[],{"categories":820},[122],{"categories":822},[128],{"categories":824},[122],{"categories":826},[122],{"categories":828},[181],{"categories":830},[164],{"categories":832},[125],{"categories":834},[],{"categories":836},[],{"categories":838},[436],{"categories":840},[174],{"categories":842},[],{"categories":844},[125],{"categories":846},[122],{"categories":848},[164,122],{"categories":850},[116],{"categories":852},[],{"categories":854},[122],{"categories":856},[116],{"categories":858},[164],{"categories":860},[125],{"categories":862},[174],{"categories":864},[],{"categories":866},[122],{"categories":868},[],{"categories":870},[116],{"categories":872},[],{"categories":874},[125],{"categories":876},[128],{"categories":878},[122],{"categories":880},[122],{"categories":882},[164],{"categories":884},[125],{"categories":886},[436],{"categories":888},[164],{"categories":890},[125],{"categories":892},[122],{"categories":894},[122],{"categories":896},[122],{"categories":898},[143],{"categories":900},[],{"categories":902},[128],{"categories":904},[125],{"categories":906},[164],{"categories":908},[125],{"categories":910},[174],{"categories":912},[164],{"categories":914},[125],{"categories":916},[143],{"categories":918},[],{"categories":920},[122],{"categories":922},[164],{"categories":924},[122],{"categories":926},[116],{"categories":928},[143],{"categories":930},[122],{"categories":932},[181],{"categories":934},[122],{"categories":936},[122],{"categories":938},[125],{"categories":940},[125],{"categories":942},[122],{"categories":944},[125],{"categories":946},[164],{"categories":948},[122],{"categories":950},[],{"categories":952},[],{"categories":954},[174],{"categories":956},[],{"categories":958},[116],{"categories":960},[436],{"categories":962},[],{"categories":964},[116],{"categories":966},[119],{"categories":968},[181],{"categories":970},[],{"categories":972},[119],{"categories":974},[],{"categories":976},[],{"categories":978},[],{"categories":980},[],{"categories":982},[],{"categories":984},[122],{"categories":986},[125],{"categories":988},[436],{"categories":990},[116],{"categories":992},[122],{"categories":994},[174],{"categories":996},[128],{"categories":998},[122],{"categories":1000},[181],{"categories":1002},[122],{"categories":1004},[122],{"categories":1006},[122],{"categories":1008},[122,116],{"categories":1010},[174],{"categories":1012},[174],{"categories":1014},[164],{"categories":1016},[122],{"categories":1018},[],{"categories":1020},[],{"categories":1022},[],{"categories":1024},[174],{"categories":1026},[167],{"categories":1028},[143],{"categories":1030},[164],{"categories":1032},[],{"categories":1034},[122],{"categories":1036},[122],{"categories":1038},[],{"categories":1040},[],{"categories":1042},[125],{"categories":1044},[122],{"categories":1046},[119],{"categories":1048},[],{"categories":1050},[116],{"categories":1052},[122],{"categories":1054},[116],{"categories":1056},[122],{"categories":1058},[174],{"categories":1060},[181],{"categories":1062},[122,164],{"categories":1064},[143],{"categories":1066},[164],{"categories":1068},[],{"categories":1070},[436],{"categories":1072},[164],{"categories":1074},[125],{"categories":1076},[],{"categories":1078},[],{"categories":1080},[],{"categories":1082},[],{"categories":1084},[174],{"categories":1086},[125],{"categories":1088},[125],{"categories":1090},[122],{"categories":1092},[122],{"categories":1094},[],{"categories":1096},[164],{"categories":1098},[],{"categories":1100},[],{"categories":1102},[125],{"categories":1104},[],{"categories":1106},[],{"categories":1108},[181],{"categories":1110},[181],{"categories":1112},[125],{"categories":1114},[],{"categories":1116},[122],{"categories":1118},[122],{"categories":1120},[174],{"categories":1122},[164],{"categories":1124},[164],{"categories":1126},[125],{"categories":1128},[116],{"categories":1130},[122],{"categories":1132},[164],{"categories":1134},[164],{"categories":1136},[125],{"categories":1138},[125],{"categories":1140},[122],{"categories":1142},[],{"categories":1144},[],{"categories":1146},[122],{"categories":1148},[125],{"categories":1150},[143],{"categories":1152},[174],{"categories":1154},[116],{"categories":1156},[122],{"categories":1158},[],{"categories":1160},[125],{"categories":1162},[125],{"categories":1164},[],{"categories":1166},[116],{"categories":1168},[122],{"categories":1170},[116],{"categories":1172},[116],{"categories":1174},[],{"categories":1176},[],{"categories":1178},[125],{"categories":1180},[125],{"categories":1182},[122],{"categories":1184},[122],{"categories":1186},[143],{"categories":1188},[167],{"categories":1190},[128],{"categories":1192},[143],{"categories":1194},[164],{"categories":1196},[],{"categories":1198},[143],{"categories":1200},[],{"categories":1202},[],{"categories":1204},[],{"categories":1206},[],{"categories":1208},[174],{"categories":1210},[167],{"categories":1212},[],{"categories":1214},[122],{"categories":1216},[122],{"categories":1218},[167],{"categories":1220},[174],{"categories":1222},[],{"categories":1224},[],{"categories":1226},[125],{"categories":1228},[143],{"categories":1230},[143],{"categories":1232},[125],{"categories":1234},[116],{"categories":1236},[122,436],{"categories":1238},[],{"categories":1240},[164],{"categories":1242},[116],{"categories":1244},[125],{"categories":1246},[164],{"categories":1248},[],{"categories":1250},[125],{"categories":1252},[125],{"categories":1254},[122],{"categories":1256},[181],{"categories":1258},[174],{"categories":1260},[164],{"categories":1262},[],{"categories":1264},[125],{"categories":1266},[122],{"categories":1268},[125],{"categories":1270},[125],{"categories":1272},[125],{"categories":1274},[181],{"categories":1276},[125],{"categories":1278},[122],{"categories":1280},[],{"categories":1282},[181],{"categories":1284},[143],{"categories":1286},[125],{"categories":1288},[],{"categories":1290},[],{"categories":1292},[122],{"categories":1294},[125],{"categories":1296},[143],{"categories":1298},[125],{"categories":1300},[],{"categories":1302},[],{"categories":1304},[],{"categories":1306},[125],{"categories":1308},[],{"categories":1310},[],{"categories":1312},[167],{"categories":1314},[122],{"categories":1316},[167],{"categories":1318},[143],{"categories":1320},[122],{"categories":1322},[122],{"categories":1324},[125],{"categories":1326},[122],{"categories":1328},[],{"categories":1330},[],{"categories":1332},[436],{"categories":1334},[],{"categories":1336},[],{"categories":1338},[116],{"categories":1340},[],{"categories":1342},[],{"categories":1344},[],{"categories":1346},[],{"categories":1348},[174],{"categories":1350},[143],{"categories":1352},[181],{"categories":1354},[119],{"categories":1356},[122],{"categories":1358},[122],{"categories":1360},[119],{"categories":1362},[],{"categories":1364},[164],{"categories":1366},[125],{"categories":1368},[119],{"categories":1370},[122],{"categories":1372},[122],{"categories":1374},[116],{"categories":1376},[],{"categories":1378},[116],{"categories":1380},[122],{"categories":1382},[181],{"categories":1384},[125],{"categories":1386},[143],{"categories":1388},[119],{"categories":1390},[122],{"categories":1392},[125],{"categories":1394},[],{"categories":1396},[122],{"categories":1398},[116],{"categories":1400},[122],{"categories":1402},[],{"categories":1404},[143],{"categories":1406},[122],{"categories":1408},[],{"categories":1410},[119],{"categories":1412},[122],{"categories":1414},[],{"categories":1416},[],{"categories":1418},[],{"categories":1420},[122],{"categories":1422},[],{"categories":1424},[436],{"categories":1426},[122],{"categories":1428},[],{"categories":1430},[122],{"categories":1432},[122],{"categories":1434},[122],{"categories":1436},[122,436],{"categories":1438},[122],{"categories":1440},[122],{"categories":1442},[164],{"categories":1444},[125],{"categories":1446},[],{"categories":1448},[125],{"categories":1450},[122],{"categories":1452},[122],{"categories":1454},[122],{"categories":1456},[116],{"categories":1458},[116],{"categories":1460},[174],{"categories":1462},[164],{"categories":1464},[125],{"categories":1466},[],{"categories":1468},[122],{"categories":1470},[143],{"categories":1472},[122],{"categories":1474},[119],{"categories":1476},[],{"categories":1478},[436],{"categories":1480},[164],{"categories":1482},[164],{"categories":1484},[125],{"categories":1486},[143],{"categories":1488},[125],{"categories":1490},[122],{"categories":1492},[],{"categories":1494},[122],{"categories":1496},[],{"categories":1498},[],{"categories":1500},[122],{"categories":1502},[122],{"categories":1504},[122],{"categories":1506},[125],{"categories":1508},[122],{"categories":1510},[],{"categories":1512},[167],{"categories":1514},[125],{"categories":1516},[],{"categories":1518},[122],{"categories":1520},[143],{"categories":1522},[],{"categories":1524},[164],{"categories":1526},[436],{"categories":1528},[143],{"categories":1530},[174],{"categories":1532},[174],{"categories":1534},[143],{"categories":1536},[143],{"categories":1538},[436],{"categories":1540},[],{"categories":1542},[143],{"categories":1544},[122],{"categories":1546},[116],{"categories":1548},[143],{"categories":1550},[],{"categories":1552},[167],{"categories":1554},[143],{"categories":1556},[174],{"categories":1558},[143],{"categories":1560},[436],{"categories":1562},[122],{"categories":1564},[122],{"categories":1566},[],{"categories":1568},[119],{"categories":1570},[],{"categories":1572},[],{"categories":1574},[122],{"categories":1576},[122],{"categories":1578},[122],{"categories":1580},[122],{"categories":1582},[],{"categories":1584},[167],{"categories":1586},[116],{"categories":1588},[],{"categories":1590},[122],{"categories":1592},[122],{"categories":1594},[436],{"categories":1596},[436],{"categories":1598},[],{"categories":1600},[125],{"categories":1602},[143],{"categories":1604},[143],{"categories":1606},[122],{"categories":1608},[125],{"categories":1610},[],{"categories":1612},[164],{"categories":1614},[122],{"categories":1616},[122],{"categories":1618},[],{"categories":1620},[],{"categories":1622},[436],{"categories":1624},[122],{"categories":1626},[174],{"categories":1628},[119],{"categories":1630},[122],{"categories":1632},[],{"categories":1634},[125],{"categories":1636},[116],{"categories":1638},[116],{"categories":1640},[],{"categories":1642},[122],{"categories":1644},[164],{"categories":1646},[125],{"categories":1648},[],{"categories":1650},[122],{"categories":1652},[122],{"categories":1654},[125],{"categories":1656},[],{"categories":1658},[125],{"categories":1660},[174],{"categories":1662},[],{"categories":1664},[122],{"categories":1666},[],{"categories":1668},[122],{"categories":1670},[],{"categories":1672},[122],{"categories":1674},[122],{"categories":1676},[],{"categories":1678},[122],{"categories":1680},[143],{"categories":1682},[122],{"categories":1684},[122],{"categories":1686},[116],{"categories":1688},[122],{"categories":1690},[143],{"categories":1692},[125],{"categories":1694},[],{"categories":1696},[122],{"categories":1698},[181],{"categories":1700},[],{"categories":1702},[],{"categories":1704},[],{"categories":1706},[116],{"categories":1708},[143],{"categories":1710},[125],{"categories":1712},[122],{"categories":1714},[164],{"categories":1716},[125],{"categories":1718},[],{"categories":1720},[125],{"categories":1722},[],{"categories":1724},[122],{"categories":1726},[125],{"categories":1728},[122],{"categories":1730},[],{"categories":1732},[122],{"categories":1734},[122],{"categories":1736},[143],{"categories":1738},[164],{"categories":1740},[125],{"categories":1742},[164],{"categories":1744},[119],{"categories":1746},[],{"categories":1748},[],{"categories":1750},[122],{"categories":1752},[116],{"categories":1754},[143],{"categories":1756},[],{"categories":1758},[],{"categories":1760},[174],{"categories":1762},[164],{"categories":1764},[],{"categories":1766},[122],{"categories":1768},[],{"categories":1770},[181],{"categories":1772},[122],{"categories":1774},[436],{"categories":1776},[174],{"categories":1778},[],{"categories":1780},[125],{"categories":1782},[122],{"categories":1784},[125],{"categories":1786},[125],{"categories":1788},[122],{"categories":1790},[],{"categories":1792},[116],{"categories":1794},[122],{"categories":1796},[119],{"categories":1798},[174],{"categories":1800},[164],{"categories":1802},[],{"categories":1804},[],{"categories":1806},[],{"categories":1808},[125],{"categories":1810},[164],{"categories":1812},[143],{"categories":1814},[122],{"categories":1816},[143],{"categories":1818},[164],{"categories":1820},[],{"categories":1822},[164],{"categories":1824},[143],{"categories":1826},[119],{"categories":1828},[122],{"categories":1830},[143],{"categories":1832},[181],{"categories":1834},[],{"categories":1836},[],{"categories":1838},[167],{"categories":1840},[122,174],{"categories":1842},[143],{"categories":1844},[122],{"categories":1846},[125],{"categories":1848},[125],{"categories":1850},[122],{"categories":1852},[],{"categories":1854},[174],{"categories":1856},[122],{"categories":1858},[167],{"categories":1860},[125],{"categories":1862},[181],{"categories":1864},[436],{"categories":1866},[],{"categories":1868},[116],{"categories":1870},[125],{"categories":1872},[125],{"categories":1874},[174],{"categories":1876},[122],{"categories":1878},[122],{"categories":1880},[],{"categories":1882},[],{"categories":1884},[],{"categories":1886},[436],{"categories":1888},[143],{"categories":1890},[122],{"categories":1892},[122],{"categories":1894},[122],{"categories":1896},[],{"categories":1898},[167],{"categories":1900},[119],{"categories":1902},[],{"categories":1904},[125],{"categories":1906},[436],{"categories":1908},[],{"categories":1910},[164],{"categories":1912},[164],{"categories":1914},[],{"categories":1916},[174],{"categories":1918},[164],{"categories":1920},[122],{"categories":1922},[],{"categories":1924},[143],{"categories":1926},[122],{"categories":1928},[164],{"categories":1930},[125],{"categories":1932},[143],{"categories":1934},[],{"categories":1936},[125],{"categories":1938},[164],{"categories":1940},[122],{"categories":1942},[],{"categories":1944},[122],{"categories":1946},[122],{"categories":1948},[436],{"categories":1950},[143],{"categories":1952},[167],{"categories":1954},[167],{"categories":1956},[],{"categories":1958},[],{"categories":1960},[],{"categories":1962},[125],{"categories":1964},[174],{"categories":1966},[174],{"categories":1968},[],{"categories":1970},[],{"categories":1972},[122],{"categories":1974},[],{"categories":1976},[125],{"categories":1978},[122],{"categories":1980},[],{"categories":1982},[122],{"categories":1984},[119],{"categories":1986},[122],{"categories":1988},[181],{"categories":1990},[125],{"categories":1992},[122],{"categories":1994},[174],{"categories":1996},[143],{"categories":1998},[125],{"categories":2000},[],{"categories":2002},[143],{"categories":2004},[125],{"categories":2006},[125],{"categories":2008},[],{"categories":2010},[119],{"categories":2012},[125],{"categories":2014},[],{"categories":2016},[122],{"categories":2018},[116],{"categories":2020},[143],{"categories":2022},[436],{"categories":2024},[125],{"categories":2026},[125],{"categories":2028},[116],{"categories":2030},[122],{"categories":2032},[],{"categories":2034},[],{"categories":2036},[164],{"categories":2038},[122,119],{"categories":2040},[],{"categories":2042},[116],{"categories":2044},[167],{"categories":2046},[122],{"categories":2048},[174],{"categories":2050},[122],{"categories":2052},[125],{"categories":2054},[122],{"categories":2056},[122],{"categories":2058},[143],{"categories":2060},[125],{"categories":2062},[],{"categories":2064},[],{"categories":2066},[125],{"categories":2068},[122],{"categories":2070},[436],{"categories":2072},[],{"categories":2074},[122],{"categories":2076},[125],{"categories":2078},[],{"categories":2080},[122],{"categories":2082},[181],{"categories":2084},[167],{"categories":2086},[125],{"categories":2088},[122],{"categories":2090},[436],{"categories":2092},[],{"categories":2094},[122],{"categories":2096},[181],{"categories":2098},[164],{"categories":2100},[122],{"categories":2102},[],{"categories":2104},[181],{"categories":2106},[143],{"categories":2108},[122],{"categories":2110},[122],{"categories":2112},[116],{"categories":2114},[],{"categories":2116},[],{"categories":2118},[164],{"categories":2120},[122],{"categories":2122},[167],{"categories":2124},[181],{"categories":2126},[181],{"categories":2128},[143],{"categories":2130},[],{"categories":2132},[],{"categories":2134},[122],{"categories":2136},[],{"categories":2138},[122,174],{"categories":2140},[143],{"categories":2142},[125],{"categories":2144},[174],{"categories":2146},[122],{"categories":2148},[116],{"categories":2150},[],{"categories":2152},[],{"categories":2154},[116],{"categories":2156},[181],{"categories":2158},[122],{"categories":2160},[],{"categories":2162},[164,122],{"categories":2164},[436],{"categories":2166},[116],{"categories":2168},[],{"categories":2170},[119],{"categories":2172},[119],{"categories":2174},[122],{"categories":2176},[174],{"categories":2178},[125],{"categories":2180},[143],{"categories":2182},[181],{"categories":2184},[164],{"categories":2186},[122],{"categories":2188},[122],{"categories":2190},[122],{"categories":2192},[116],{"categories":2194},[122],{"categories":2196},[125],{"categories":2198},[143],{"categories":2200},[],{"categories":2202},[],{"categories":2204},[167],{"categories":2206},[174],{"categories":2208},[122],{"categories":2210},[164],{"categories":2212},[167],{"categories":2214},[122],{"categories":2216},[122],{"categories":2218},[125],{"categories":2220},[125],{"categories":2222},[122,119],{"categories":2224},[],{"categories":2226},[164],{"categories":2228},[],{"categories":2230},[122],{"categories":2232},[143],{"categories":2234},[116],{"categories":2236},[116],{"categories":2238},[125],{"categories":2240},[122],{"categories":2242},[119],{"categories":2244},[174],{"categories":2246},[181],{"categories":2248},[],{"categories":2250},[143],{"categories":2252},[122],{"categories":2254},[122],{"categories":2256},[143],{"categories":2258},[174],{"categories":2260},[122],{"categories":2262},[125],{"categories":2264},[143],{"categories":2266},[122],{"categories":2268},[164],{"categories":2270},[122],{"categories":2272},[122],{"categories":2274},[436],{"categories":2276},[128],{"categories":2278},[125],{"categories":2280},[122],{"categories":2282},[143],{"categories":2284},[125],{"categories":2286},[181],{"categories":2288},[122],{"categories":2290},[],{"categories":2292},[122],{"categories":2294},[],{"categories":2296},[],{"categories":2298},[],{"categories":2300},[119],{"categories":2302},[122],{"categories":2304},[125],{"categories":2306},[143],{"categories":2308},[143],{"categories":2310},[143],{"categories":2312},[143],{"categories":2314},[],{"categories":2316},[116],{"categories":2318},[125],{"categories":2320},[143],{"categories":2322},[116],{"categories":2324},[125],{"categories":2326},[122],{"categories":2328},[122,125],{"categories":2330},[125],{"categories":2332},[436],{"categories":2334},[143],{"categories":2336},[143],{"categories":2338},[125],{"categories":2340},[122],{"categories":2342},[],{"categories":2344},[143],{"categories":2346},[181],{"categories":2348},[116],{"categories":2350},[122],{"categories":2352},[122],{"categories":2354},[],{"categories":2356},[174],{"categories":2358},[],{"categories":2360},[116],{"categories":2362},[125],{"categories":2364},[143],{"categories":2366},[122],{"categories":2368},[143],{"categories":2370},[116],{"categories":2372},[143],{"categories":2374},[143],{"categories":2376},[],{"categories":2378},[119],{"categories":2380},[125],{"categories":2382},[143],{"categories":2384},[143],{"categories":2386},[143],{"categories":2388},[143],{"categories":2390},[143],{"categories":2392},[143],{"categories":2394},[143],{"categories":2396},[143],{"categories":2398},[143],{"categories":2400},[143],{"categories":2402},[167],{"categories":2404},[116],{"categories":2406},[122],{"categories":2408},[122],{"categories":2410},[],{"categories":2412},[122,116],{"categories":2414},[],{"categories":2416},[125],{"categories":2418},[143],{"categories":2420},[125],{"categories":2422},[122],{"categories":2424},[122],{"categories":2426},[122],{"categories":2428},[122],{"categories":2430},[122],{"categories":2432},[125],{"categories":2434},[119],{"categories":2436},[164],{"categories":2438},[143],{"categories":2440},[122],{"categories":2442},[],{"categories":2444},[],{"categories":2446},[125],{"categories":2448},[164],{"categories":2450},[122],{"categories":2452},[],{"categories":2454},[],{"categories":2456},[181],{"categories":2458},[122],{"categories":2460},[],{"categories":2462},[],{"categories":2464},[116],{"categories":2466},[119],{"categories":2468},[122],{"categories":2470},[119],{"categories":2472},[164],{"categories":2474},[],{"categories":2476},[143],{"categories":2478},[],{"categories":2480},[164],{"categories":2482},[122],{"categories":2484},[181],{"categories":2486},[],{"categories":2488},[181],{"categories":2490},[],{"categories":2492},[],{"categories":2494},[125],{"categories":2496},[],{"categories":2498},[119],{"categories":2500},[116],{"categories":2502},[164],{"categories":2504},[174],{"categories":2506},[],{"categories":2508},[],{"categories":2510},[122],{"categories":2512},[116],{"categories":2514},[181],{"categories":2516},[],{"categories":2518},[125],{"categories":2520},[125],{"categories":2522},[143],{"categories":2524},[122],{"categories":2526},[125],{"categories":2528},[122],{"categories":2530},[125],{"categories":2532},[122],{"categories":2534},[128],{"categories":2536},[143],{"categories":2538},[],{"categories":2540},[181],{"categories":2542},[174],{"categories":2544},[125],{"categories":2546},[],{"categories":2548},[122],{"categories":2550},[125],{"categories":2552},[119],{"categories":2554},[116],{"categories":2556},[122],{"categories":2558},[164],{"categories":2560},[174],{"categories":2562},[174],{"categories":2564},[122],{"categories":2566},[167],{"categories":2568},[122],{"categories":2570},[125],{"categories":2572},[119],{"categories":2574},[125],{"categories":2576},[122],{"categories":2578},[122],{"categories":2580},[125],{"categories":2582},[143],{"categories":2584},[],{"categories":2586},[116],{"categories":2588},[122],{"categories":2590},[125],{"categories":2592},[122],{"categories":2594},[122],{"categories":2596},[],{"categories":2598},[164],{"categories":2600},[119],{"categories":2602},[143],{"categories":2604},[122],{"categories":2606},[122],{"categories":2608},[164],{"categories":2610},[181],{"categories":2612},[167],{"categories":2614},[122],{"categories":2616},[143],{"categories":2618},[122],{"categories":2620},[125],{"categories":2622},[436],{"categories":2624},[122],{"categories":2626},[125],{"categories":2628},[167],{"categories":2630},[],{"categories":2632},[125],{"categories":2634},[174],{"categories":2636},[164],{"categories":2638},[122],{"categories":2640},[116],{"categories":2642},[119],{"categories":2644},[174],{"categories":2646},[],{"categories":2648},[125],{"categories":2650},[122],{"categories":2652},[],{"categories":2654},[143],{"categories":2656},[],{"categories":2658},[143],{"categories":2660},[122],{"categories":2662},[125],{"categories":2664},[125],{"categories":2666},[125],{"categories":2668},[],{"categories":2670},[],{"categories":2672},[122],{"categories":2674},[122],{"categories":2676},[],{"categories":2678},[164],{"categories":2680},[125],{"categories":2682},[181],{"categories":2684},[116],{"categories":2686},[],{"categories":2688},[],{"categories":2690},[143],{"categories":2692},[174],{"categories":2694},[122],{"categories":2696},[122],{"categories":2698},[122],{"categories":2700},[174],{"categories":2702},[143],{"categories":2704},[164],{"categories":2706},[122],{"categories":2708},[122],{"categories":2710},[122],{"categories":2712},[143],{"categories":2714},[122],{"categories":2716},[143],{"categories":2718},[125],{"categories":2720},[125],{"categories":2722},[174],{"categories":2724},[125],{"categories":2726},[122],{"categories":2728},[174],{"categories":2730},[164],{"categories":2732},[],{"categories":2734},[125],{"categories":2736},[],{"categories":2738},[],{"categories":2740},[119],{"categories":2742},[122],{"categories":2744},[125],{"categories":2746},[116],{"categories":2748},[125],{"categories":2750},[181],{"categories":2752},[],{"categories":2754},[125],{"categories":2756},[],{"categories":2758},[116],{"categories":2760},[125],{"categories":2762},[],{"categories":2764},[125],{"categories":2766},[122],{"categories":2768},[143],{"categories":2770},[122],{"categories":2772},[125],{"categories":2774},[143],{"categories":2776},[125],{"categories":2778},[174],{"categories":2780},[164],{"categories":2782},[116],{"categories":2784},[],{"categories":2786},[125],{"categories":2788},[164],{"categories":2790},[143],{"categories":2792},[122],{"categories":2794},[164],{"categories":2796},[116],{"categories":2798},[],{"categories":2800},[125],{"categories":2802},[125],{"categories":2804},[122],{"categories":2806},[],{"categories":2808},[125],{"categories":2810},[128],{"categories":2812},[143],{"categories":2814},[125],{"categories":2816},[119],{"categories":2818},[],{"categories":2820},[122],{"categories":2822},[128],{"categories":2824},[122],{"categories":2826},[125],{"categories":2828},[143],{"categories":2830},[116],{"categories":2832},[436],{"categories":2834},[122],{"categories":2836},[122],{"categories":2838},[122],{"categories":2840},[143],{"categories":2842},[119],{"categories":2844},[122],{"categories":2846},[164],{"categories":2848},[143],{"categories":2850},[436],{"categories":2852},[122],{"categories":2854},[],{"categories":2856},[],{"categories":2858},[436],{"categories":2860},[167],{"categories":2862},[125],{"categories":2864},[125],{"categories":2866},[143],{"categories":2868},[122],{"categories":2870},[116],{"categories":2872},[164],{"categories":2874},[125],{"categories":2876},[122],{"categories":2878},[181],{"categories":2880},[122],{"categories":2882},[125],{"categories":2884},[],{"categories":2886},[122],{"categories":2888},[122],{"categories":2890},[143],{"categories":2892},[116],{"categories":2894},[],{"categories":2896},[122],{"categories":2898},[122],{"categories":2900},[174],{"categories":2902},[164],{"categories":2904},[122,125],{"categories":2906},[181,119],{"categories":2908},[122],{"categories":2910},[],{"categories":2912},[125],{"categories":2914},[],{"categories":2916},[174],{"categories":2918},[122],{"categories":2920},[143],{"categories":2922},[],{"categories":2924},[125],{"categories":2926},[],{"categories":2928},[125],{"categories":2930},[116],{"categories":2932},[125],{"categories":2934},[122],{"categories":2936},[436],{"categories":2938},[181],{"categories":2940},[119],{"categories":2942},[119],{"categories":2944},[116],{"categories":2946},[116],{"categories":2948},[122],{"categories":2950},[125],{"categories":2952},[122],{"categories":2954},[122],{"categories":2956},[116],{"categories":2958},[122],{"categories":2960},[181],{"categories":2962},[143],{"categories":2964},[122],{"categories":2966},[125],{"categories":2968},[122],{"categories":2970},[],{"categories":2972},[174],{"categories":2974},[],{"categories":2976},[125],{"categories":2978},[116],{"categories":2980},[],{"categories":2982},[436],{"categories":2984},[122],{"categories":2986},[],{"categories":2988},[143],{"categories":2990},[125],{"categories":2992},[174],{"categories":2994},[122],{"categories":2996},[125],{"categories":2998},[174],{"categories":3000},[125],{"categories":3002},[143],{"categories":3004},[116],{"categories":3006},[143],{"categories":3008},[174],{"categories":3010},[122],{"categories":3012},[164],{"categories":3014},[122],{"categories":3016},[122],{"categories":3018},[122],{"categories":3020},[122],{"categories":3022},[125],{"categories":3024},[122],{"categories":3026},[125],{"categories":3028},[122],{"categories":3030},[116],{"categories":3032},[122],{"categories":3034},[125],{"categories":3036},[164],{"categories":3038},[116],{"categories":3040},[125],{"categories":3042},[164],{"categories":3044},[],{"categories":3046},[122],{"categories":3048},[122],{"categories":3050},[174],{"categories":3052},[],{"categories":3054},[125],{"categories":3056},[181],{"categories":3058},[122],{"categories":3060},[143],{"categories":3062},[181],{"categories":3064},[125],{"categories":3066},[119],{"categories":3068},[119],{"categories":3070},[122],{"categories":3072},[116],{"categories":3074},[],{"categories":3076},[122],{"categories":3078},[],{"categories":3080},[116],{"categories":3082},[122],{"categories":3084},[125],{"categories":3086},[125],{"categories":3088},[],{"categories":3090},[174],{"categories":3092},[174],{"categories":3094},[181],{"categories":3096},[164],{"categories":3098},[],{"categories":3100},[122],{"categories":3102},[116],{"categories":3104},[122],{"categories":3106},[174],{"categories":3108},[116],{"categories":3110},[143],{"categories":3112},[143],{"categories":3114},[],{"categories":3116},[143],{"categories":3118},[125],{"categories":3120},[164],{"categories":3122},[167],{"categories":3124},[122],{"categories":3126},[],{"categories":3128},[143],{"categories":3130},[174],{"categories":3132},[119],{"categories":3134},[122],{"categories":3136},[116],{"categories":3138},[436],{"categories":3140},[116],{"categories":3142},[],{"categories":3144},[],{"categories":3146},[143],{"categories":3148},[],{"categories":3150},[125],{"categories":3152},[125],{"categories":3154},[125],{"categories":3156},[],{"categories":3158},[122],{"categories":3160},[],{"categories":3162},[143],{"categories":3164},[116],{"categories":3166},[164],{"categories":3168},[122],{"categories":3170},[143],{"categories":3172},[143],{"categories":3174},[],{"categories":3176},[143],{"categories":3178},[116],{"categories":3180},[122],{"categories":3182},[],{"categories":3184},[125],{"categories":3186},[125],{"categories":3188},[116],{"categories":3190},[],{"categories":3192},[],{"categories":3194},[],{"categories":3196},[164],{"categories":3198},[125],{"categories":3200},[122],{"categories":3202},[],{"categories":3204},[],{"categories":3206},[],{"categories":3208},[164],{"categories":3210},[],{"categories":3212},[116],{"categories":3214},[],{"categories":3216},[],{"categories":3218},[164],{"categories":3220},[122],{"categories":3222},[143],{"categories":3224},[],{"categories":3226},[181],{"categories":3228},[143],{"categories":3230},[181],{"categories":3232},[122],{"categories":3234},[],{"categories":3236},[],{"categories":3238},[125],{"categories":3240},[],{"categories":3242},[],{"categories":3244},[125],{"categories":3246},[122],{"categories":3248},[],{"categories":3250},[125],{"categories":3252},[143],{"categories":3254},[181],{"categories":3256},[167],{"categories":3258},[125],{"categories":3260},[125],{"categories":3262},[],{"categories":3264},[],{"categories":3266},[],{"categories":3268},[143],{"categories":3270},[],{"categories":3272},[],{"categories":3274},[164],{"categories":3276},[116],{"categories":3278},[],{"categories":3280},[119],{"categories":3282},[181],{"categories":3284},[122],{"categories":3286},[174],{"categories":3288},[116],{"categories":3290},[167],{"categories":3292},[119],{"categories":3294},[174],{"categories":3296},[],{"categories":3298},[],{"categories":3300},[125],{"categories":3302},[116],{"categories":3304},[164],{"categories":3306},[116],{"categories":3308},[125],{"categories":3310},[436],{"categories":3312},[125],{"categories":3314},[],{"categories":3316},[122],{"categories":3318},[143],{"categories":3320},[174],{"categories":3322},[],{"categories":3324},[164],{"categories":3326},[143],{"categories":3328},[116],{"categories":3330},[125],{"categories":3332},[122],{"categories":3334},[119],{"categories":3336},[125,436],{"categories":3338},[125],{"categories":3340},[174],{"categories":3342},[122],{"categories":3344},[167],{"categories":3346},[181],{"categories":3348},[125],{"categories":3350},[],{"categories":3352},[125],{"categories":3354},[122],{"categories":3356},[119],{"categories":3358},[],{"categories":3360},[],{"categories":3362},[122],{"categories":3364},[167],{"categories":3366},[122],{"categories":3368},[],{"categories":3370},[143],{"categories":3372},[],{"categories":3374},[143],{"categories":3376},[174],{"categories":3378},[125],{"categories":3380},[122],{"categories":3382},[181],{"categories":3384},[174],{"categories":3386},[],{"categories":3388},[143],{"categories":3390},[122],{"categories":3392},[],{"categories":3394},[122],{"categories":3396},[125],{"categories":3398},[122],{"categories":3400},[125],{"categories":3402},[122],{"categories":3404},[122],{"categories":3406},[122],{"categories":3408},[122],{"categories":3410},[119],{"categories":3412},[],{"categories":3414},[128],{"categories":3416},[143],{"categories":3418},[122],{"categories":3420},[],{"categories":3422},[174],{"categories":3424},[122],{"categories":3426},[122],{"categories":3428},[125],{"categories":3430},[143],{"categories":3432},[122],{"categories":3434},[122],{"categories":3436},[119],{"categories":3438},[125],{"categories":3440},[164],{"categories":3442},[],{"categories":3444},[167],{"categories":3446},[122],{"categories":3448},[],{"categories":3450},[143],{"categories":3452},[181],{"categories":3454},[],{"categories":3456},[],{"categories":3458},[143],{"categories":3460},[143],{"categories":3462},[181],{"categories":3464},[116],{"categories":3466},[125],{"categories":3468},[125],{"categories":3470},[122],{"categories":3472},[119],{"categories":3474},[],{"categories":3476},[],{"categories":3478},[143],{"categories":3480},[167],{"categories":3482},[174],{"categories":3484},[125],{"categories":3486},[164],{"categories":3488},[167],{"categories":3490},[167],{"categories":3492},[],{"categories":3494},[143],{"categories":3496},[122],{"categories":3498},[122],{"categories":3500},[174],{"categories":3502},[],{"categories":3504},[143],{"categories":3506},[143],{"categories":3508},[143],{"categories":3510},[],{"categories":3512},[125],{"categories":3514},[122],{"categories":3516},[],{"categories":3518},[116],{"categories":3520},[119],{"categories":3522},[],{"categories":3524},[122],{"categories":3526},[122],{"categories":3528},[],{"categories":3530},[174],{"categories":3532},[],{"categories":3534},[],{"categories":3536},[],{"categories":3538},[],{"categories":3540},[122],{"categories":3542},[143],{"categories":3544},[],{"categories":3546},[],{"categories":3548},[122],{"categories":3550},[122],{"categories":3552},[122],{"categories":3554},[167],{"categories":3556},[122],{"categories":3558},[167],{"categories":3560},[],{"categories":3562},[167],{"categories":3564},[167],{"categories":3566},[436],{"categories":3568},[125],{"categories":3570},[174],{"categories":3572},[],{"categories":3574},[],{"categories":3576},[167],{"categories":3578},[174],{"categories":3580},[174],{"categories":3582},[174],{"categories":3584},[],{"categories":3586},[116],{"categories":3588},[174],{"categories":3590},[174],{"categories":3592},[116],{"categories":3594},[174],{"categories":3596},[119],{"categories":3598},[174],{"categories":3600},[174],{"categories":3602},[174],{"categories":3604},[167],{"categories":3606},[143],{"categories":3608},[143],{"categories":3610},[122],{"categories":3612},[174],{"categories":3614},[167],{"categories":3616},[436],{"categories":3618},[167],{"categories":3620},[167],{"categories":3622},[167],{"categories":3624},[],{"categories":3626},[119],{"categories":3628},[],{"categories":3630},[436],{"categories":3632},[174],{"categories":3634},[174],{"categories":3636},[174],{"categories":3638},[125],{"categories":3640},[143,119],{"categories":3642},[167],{"categories":3644},[],{"categories":3646},[],{"categories":3648},[167],{"categories":3650},[],{"categories":3652},[167],{"categories":3654},[143],{"categories":3656},[125],{"categories":3658},[],{"categories":3660},[174],{"categories":3662},[122],{"categories":3664},[164],{"categories":3666},[],{"categories":3668},[122],{"categories":3670},[],{"categories":3672},[143],{"categories":3674},[116],{"categories":3676},[167],{"categories":3678},[],{"categories":3680},[174],{"categories":3682},[143],[3684,3760,3858,3932],{"id":3685,"title":3686,"ai":3687,"body":3692,"categories":3733,"created_at":64,"date_modified":64,"description":56,"extension":65,"faq":64,"featured":66,"kicker_label":64,"meta":3734,"navigation":96,"path":3747,"published_at":3748,"question":64,"scraped_at":3749,"seo":3750,"sitemap":3751,"source_id":3752,"source_name":3753,"source_type":103,"source_url":3754,"stem":3755,"tags":3756,"thumbnail_url":64,"tldr":3757,"tweet":64,"unknown_tags":3758,"__hash__":3759},"summaries\u002Fsummaries\u002F1b682c7e4ee45c46-637mb-llm-runs-offline-on-base-macbook-air-works-s-summary.md","637MB LLM Runs Offline on Base MacBook Air, Works Surprisingly Well",{"provider":7,"model":8,"input_tokens":3688,"output_tokens":3689,"processing_time_ms":3690,"cost_usd":3691},5208,1356,14310,0.00121275,{"type":14,"value":3693,"toc":3728},[3694,3698,3714,3718,3721,3725],[17,3695,3697],{"id":3696},"effortless-local-setup-delivers-instant-offline-inference","Effortless Local Setup Delivers Instant, Offline Inference",[22,3699,3700,3701,3705,3706,3709,3710,3713],{},"Install Ollama with ",[3702,3703,3704],"code",{},"brew install ollama",", start the server via ",[3702,3707,3708],{},"ollama serve",", and load TinyLlama—a 700MB model based on Llama 2—with ",[3702,3711,3712],{},"ollama run tinyllama",". This three-command process skips Docker, Python environments, API keys, and accounts, downloading the model once for subsequent instant loads. On a base MacBook Air (no GPU or cooling upgrades), responses stream without latency, spinners, or internet—working in tunnels or planes with zero data telemetry, rate limits, or quotas. Tokens appear as fast as local typing, shifting AI from remote servers to a self-contained file.",[17,3715,3717],{"id":3716},"handles-practical-tasks-like-a-junior-dev-fails-on-complexity","Handles Practical Tasks Like a Junior Dev, Fails on Complexity",[22,3719,3720],{},"TinyLlama generates a fully functional Node.js Express server with routes, middleware, error handling, and comments—copy-paste runnable without edits. In casual conversations, it explains REST vs. GraphQL differences naturally, matching a coworker's tone and gently correcting user errors without robotic disclaimers. Limits emerge in long contexts (forgets details), multi-step reasoning (loses track of ideas), and hallucinations (invents nonexistent libraries). Failures resemble a junior developer's gaps—coherent but bounded—not random nonsense, making it viable for autocomplete, email rewrites, error explanations, and summaries.",[17,3722,3724],{"id":3723},"lowers-ai-floor-for-privacy-accessibility-and-everyday-use","Lowers AI Floor for Privacy, Accessibility, and Everyday Use",[22,3726,3727],{},"This setup democratizes AI: embed models in apps for offline assistants, enable learning in low-connectivity areas, process sensitive data without third-party uploads, and eliminate per-token costs. For the 'long tail' of routine tasks, small local models suffice, decoupling utility from massive scale, GPUs, and cloud bills. Frontier models still dominate complex reasoning, but the baseline shifts from paid APIs to free laptop files—challenging 'bigger is always better' narratives. Next steps include editor-integrated coding aids, personal fine-tunes on notes, multi-agent small-model collaborations, and offline RAG over documents.",{"title":56,"searchDepth":57,"depth":57,"links":3729},[3730,3731,3732],{"id":3696,"depth":57,"text":3697},{"id":3716,"depth":57,"text":3717},{"id":3723,"depth":57,"text":3724},[122],{"content_references":3735,"triage":3743},[3736,3739,3741],{"type":81,"title":3737,"context":3738},"TinyLlama","recommended",{"type":81,"title":3740,"context":3738},"Ollama",{"type":88,"title":3742,"context":84},"Llama 2",{"relevance":93,"novelty":3744,"quality":93,"actionability":93,"composite":3745,"reasoning":3746},3,3.8,"Category: AI & LLMs. The article discusses the practical application of a lightweight LLM that can run offline, addressing the audience's pain point of integrating AI into their products without heavy infrastructure. It provides a clear setup process and examples of practical tasks the model can handle, making it actionable for developers.","\u002Fsummaries\u002F1b682c7e4ee45c46-637mb-llm-runs-offline-on-base-macbook-air-works-s-summary","2026-05-05 18:01:01","2026-05-06 16:13:47",{"title":3686,"description":56},{"loc":3747},"1b682c7e4ee45c46","Towards AI","https:\u002F\u002Fpub.towardsai.net\u002Fi-ran-a-637mb-llm-on-my-base-macbook-air-and-now-im-questioning-everything-cd78287d0ccc?source=rss----98111c9905da---4","summaries\u002F1b682c7e4ee45c46-637mb-llm-runs-offline-on-base-macbook-air-works-s-summary",[109,108,107],"TinyLlama, a 637MB open-source LLM, runs instantly on a stock MacBook Air via Ollama—no internet, GPU, or API needed—handling Node.js servers and casual chats effectively, lowering the bar for useful local AI.",[],"q08Qvpflcgj-8E3EIjojpd_j_dc9AsoFnv5ZNE-FrQc",{"id":3761,"title":3762,"ai":3763,"body":3768,"categories":3809,"created_at":64,"date_modified":64,"description":56,"extension":65,"faq":64,"featured":66,"kicker_label":64,"meta":3810,"navigation":96,"path":3845,"published_at":3846,"question":64,"scraped_at":3847,"seo":3848,"sitemap":3849,"source_id":3850,"source_name":3851,"source_type":103,"source_url":3852,"stem":3853,"tags":3854,"thumbnail_url":64,"tldr":3855,"tweet":64,"unknown_tags":3856,"__hash__":3857},"summaries\u002Fsummaries\u002F6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary.md","Pick Gemma 4 Model by Hardware to Unlock 9\u002F10 Math Accuracy",{"provider":7,"model":8,"input_tokens":3764,"output_tokens":3765,"processing_time_ms":3766,"cost_usd":3767},6736,2210,15095,0.00242955,{"type":14,"value":3769,"toc":3804},[3770,3774,3777,3780,3784,3787,3790,3794,3801],[17,3771,3773],{"id":3772},"hardware-matched-model-selection-maximizes-performance","Hardware-Matched Model Selection Maximizes Performance",[22,3775,3776],{},"Gemma 4 offers four variants tailored to hardware tiers, preventing the common error of loading oversized models that seem \"broken\" due to memory shortages or slow inference. E2B (2.3B params, 3-5GB RAM) fits phones and Raspberry Pi 5 (5 tokens\u002Fsec chatting speed), prioritizing privacy for summaries\u002Fquick replies over complex coding—Google embeds it in future Pixels. E4B (4.5B params, 5-6GB) suits 8-16GB laptops like MacBook Air, handling multimodal inputs (audio\u002Fimages) for local chat\u002Fdocument Q&A but falters on multi-step agents. The 26B MoE model activates only 4B params at once (16-18GB load, plan 24GB total), delivering flagship quality at 4B-model speed with 250k token context—ranks #6 on LMSYS Arena open models. Flagship 31B (30B params, 17-20GB weights + headroom to 24GB VRAM) tops at #3 open on Arena, hits 89% on Olympiad math\u002Fcompetitive programming (master-level), and beats larger closed models like Claude Sonnet on agentic business sims—ideal for workstations with NVIDIA\u002FApple Silicon.",[22,3778,3779],{},"Decision tree: Phones\u002FPi → E2B; 8-16GB laptops → E4B; 24GB system → 26B; 24GB+ VRAM\u002FMac 32GB → 31B. Avoid aggressive quantization on MoE models, as it tanks quality.",[17,3781,3783],{"id":3782},"benchmarks-show-massive-gains-but-real-world-speed-needs-tricks","Benchmarks Show Massive Gains, But Real-World Speed Needs Tricks",[22,3785,3786],{},"Gemma 4 leaps year-over-year: prior small models solved 1-in-5 math problems; now 9-in-10 across sizes. 31B matches Qwen 3.5\u002FKimi K2.5 head-to-head on Arena despite fewer active params via MoE. Strong for one-shot coding\u002Fmath (beats most humans on programming sites) but skip for long tool-call chains—closed models edge it on chained agents.",[22,3788,3789],{},"Free 29% speed boost (50% on code): Pair 31B drafter with E2B guesser via speculative decoding (shared vocab enables it), loading both in 24GB. Use LM Studio's advanced docs for setup. This yields production speeds without hardware upgrades, turning flagship quality into practical desktop use.",[17,3791,3793],{"id":3792},"essential-tools-and-fixes-for-reliable-local-runs","Essential Tools and Fixes for Reliable Local Runs",[22,3795,3796,3797,3800],{},"Run offline\u002Fprivate on any OS: Windows\u002FMac → Ollama (one-line install: ",[3702,3798,3799],{},"ollama run gemma4",") or LM Studio (GUI chat); Linux → same + llama.cpp\u002FvLLM for 31B speed squeezes; Phones → E2B via dedicated mobile guides.",[22,3802,3803],{},"Three fixes avoid early adopter pitfalls: (1) Use latest file formats\u002Fruntime—initial uploads had tokenizer bug (garbled text\u002Ftool calls, fixed in llama.cpp PR #21343 or re-uploads). (2) Stick to baked-in settings (e.g., Google's recommended temp\u002Fsampling). (3) For looped tool calls, test community tweaks for agent reliability. Unsloth Hugging Face quants help load times. All under Apache 2.0, multimodal-ready, setup \u003C10min.",{"title":56,"searchDepth":57,"depth":57,"links":3805},[3806,3807,3808],{"id":3772,"depth":57,"text":3773},{"id":3782,"depth":57,"text":3783},{"id":3792,"depth":57,"text":3793},[122],{"content_references":3811,"triage":3843},[3812,3817,3821,3823,3826,3829,3831,3834,3837,3840],{"type":3813,"title":3814,"author":3815,"url":3816,"context":84},"report","Gemma 4 announcement","Google","https:\u002F\u002Fblog.google\u002Ftechnology\u002Fdevelopers\u002Fgemma-4\u002F",{"type":3813,"title":3818,"author":3819,"url":3820,"context":84},"Gemma 4 model card","Google AI","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fcore\u002Fmodel_card_4",{"type":81,"title":3740,"url":3822,"context":84},"https:\u002F\u002Follama.com",{"type":81,"title":3824,"url":3825,"context":84},"LM Studio","https:\u002F\u002Flmstudio.ai",{"type":81,"title":3827,"url":3828,"context":84},"llama.cpp","https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp",{"type":81,"title":86,"url":3830,"context":84},"https:\u002F\u002Fdocs.vllm.ai",{"type":88,"title":3832,"url":3833,"context":84},"LMArena leaderboard","https:\u002F\u002Flmarena.ai",{"type":81,"title":3835,"url":3836,"context":84},"Unsloth re-quants","https:\u002F\u002Fhuggingface.co\u002Funsloth",{"type":88,"title":3838,"url":3839,"context":84},"llama.cpp tokenizer fix (PR #21343)","https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\u002Fpull\u002F21343",{"type":88,"title":3841,"url":3842,"context":84},"LM Studio speculative decoding docs","https:\u002F\u002Flmstudio.ai\u002Fdocs\u002Fapp\u002Fadvanced\u002Fspeculative-decoding",{"relevance":93,"novelty":3744,"quality":93,"actionability":93,"composite":3745,"reasoning":3844},"Category: AI & LLMs. The article provides specific insights into selecting AI models based on hardware capabilities, addressing the audience's need for practical applications in building AI-powered products. It includes actionable advice on pairing models for performance boosts, which is directly applicable to developers and founders.","\u002Fsummaries\u002F6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary","2026-04-19 21:52:44","2026-04-21 15:22:05",{"title":3762,"description":56},{"loc":3845},"b698467bc8ca5e8d","DIY Smart Code","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SLOqlEmuy5U","summaries\u002F6b2accfa125e6e3e-pick-gemma-4-model-by-hardware-to-unlock-9-10-math-summary",[109,107,108],"Gemma 4's four models—E2B (3-5GB phone), E4B (5-6GB laptop), 26B MoE (16-18GB mid-tier), 31B (20-24GB flagship)—jump math benchmarks from 1\u002F5 to 9\u002F10 correct. Pair 31B+E2B for 29% speed boost. Use Ollama\u002FLM Studio for easy local runs.",[],"ua65HuwxIouruqLL41l8OC1Al-b2RnWySeAG_lZ4SOA",{"id":3859,"title":3860,"ai":3861,"body":3866,"categories":3897,"created_at":64,"date_modified":64,"description":56,"extension":65,"faq":64,"featured":66,"kicker_label":64,"meta":3898,"navigation":96,"path":3919,"published_at":3920,"question":64,"scraped_at":3921,"seo":3922,"sitemap":3923,"source_id":3924,"source_name":3925,"source_type":103,"source_url":3926,"stem":3927,"tags":3928,"thumbnail_url":64,"tldr":3929,"tweet":64,"unknown_tags":3930,"__hash__":3931},"summaries\u002Fsummaries\u002F0620e2900fa5d4a4-small-open-llms-replicate-claude-mythos-bug-hunts-summary.md","Small open LLMs replicate Claude Mythos bug hunts",{"provider":7,"model":8,"input_tokens":3862,"output_tokens":3863,"processing_time_ms":3864,"cost_usd":3865},5310,2704,20579,0.00239135,{"type":14,"value":3867,"toc":3892},[3868,3872,3875,3878,3882,3885,3889],[17,3869,3871],{"id":3870},"open-models-nail-high-profile-bugs-without-mythos","Open Models Nail High-Profile Bugs Without Mythos",[22,3873,3874],{},"Anthropic's Claude Mythos demoed autonomous bug discovery and exploitation, like the FreeBSD NFS memory bug (CVE-2026-4747), where it squeezes 1,000+ byte payloads into 304 bytes via 15 split network requests. But AISLE's tests show eight small open models—including GPT-OSS-20b (3.6B params, $0.11\u002FM tokens) and Kimi K2—all flagged this critical buffer overflow. They explained OS protections' irrelevance and proposed viable exploits; GPT-OSS-120b generated a near-real gadget chain, and Kimi K2 spotted auto-spreading attacks unmentioned by Anthropic. AISLE reported 15 OpenSSL and 5 curl vulns using similar setups. Vidoc paired GPT-5.4 and Claude Opus 4.6 with OpenCode agent to match these on Botan certificate flaws (logic gap caught 3\u002F3 runs) and wolfSSL crypto misreads, at under $30 per scanned file.",[22,3876,3877],{},"For fake vulns, like discarded user input in DB queries, small opens like Deepseek R1 and Kimi K2 succeeded every time, outperforming GPT-5.4 (0\u002F3) and some Claude versions (Sonnet 4.5 traced data wrong). Post-patch recognition lags: only GPT-OSS-120b reliably deemed fixed FreeBSD code safe; smaller models hallucinated issues.",[17,3879,3881],{"id":3880},"jagged-frontier-no-model-dominates-all-tasks","Jagged Frontier: No Model Dominates All Tasks",[22,3883,3884],{},"Capabilities spike unevenly. On OpenBSD integer overflow, GPT-OSS-120b rebuilt the full exploit chain and proposed the exact patch in one run, while Qwen3-32B (strong on FreeBSD) called code \"robust.\" Claude Opus 4.6 hit 3\u002F3, GPT-5.4 missed entirely. This \"jagged frontier\" means rankings flip per bug—pick models task-specifically, as no single frontier model wins universally.",[17,3886,3888],{"id":3887},"build-systems-not-model-worship-for-bug-hunting","Build Systems, Not Model Worship, for Bug Hunting",[22,3890,3891],{},"Mythos' edge shrinks to deployable exploits, but studies stress full pipelines: target selection, step-wise analysis, validation, prioritization, false-positive filtering. Small opens suffice for broad scanning—\"a thousand adequate detectives everywhere beat one brilliant guesser,\" per AISLE's Fort. Anthropic limits Mythos access via Project Glasswing (11 orgs) citing risks, but replications erode exclusivity claims. FT reports compute shortages delay wider release, fueling fears of hype. Use cheap opens + agents for production cybersecurity: scan widely, iterate workflows, and close the gap to proprietary models today.",{"title":56,"searchDepth":57,"depth":57,"links":3893},[3894,3895,3896],{"id":3870,"depth":57,"text":3871},{"id":3880,"depth":57,"text":3881},{"id":3887,"depth":57,"text":3888},[],{"content_references":3899,"triage":3916},[3900,3903,3907,3910,3912],{"type":81,"title":3901,"url":3902,"context":84},"Claude Mythos Preview","https:\u002F\u002Fthe-decoder.com\u002Ffrom-gpt-2-to-claude-mythos-the-return-of-ai-models-deemed-too-dangerous-to-release\u002F",{"type":88,"title":3904,"author":3905,"url":3906,"context":73},"AI Cybersecurity After Mythos: The Jagged Frontier","Stanislav Fort","https:\u002F\u002Faisle.com\u002Fblog\u002Fai-cybersecurity-after-mythos-the-jagged-frontier",{"type":88,"title":3908,"url":3909,"context":73},"We Reproduced Anthropic's Mythos Findings with Public Models","https:\u002F\u002Fblog.vidocsecurity.com\u002Fblog\u002Fwe-reproduced-anthropics-mythos-findings-with-public-models",{"type":3813,"title":3911,"context":73},"Audit by UK's AI Security Institute",{"type":88,"title":3913,"publisher":3914,"url":3915,"context":73},"Anthropic holding back model until compute ready","Financial Times","https:\u002F\u002Fwww.ft.com\u002Fcontent\u002Fc9f5b690-a10e-4c66-9245-017f8bfbc7b4?syn-25a6b1a6=1",{"relevance":3744,"novelty":3744,"quality":93,"actionability":57,"composite":3917,"reasoning":3918},3.05,"Category: AI & LLMs. The article discusses the performance of small open LLMs in cybersecurity bug detection, which is relevant to AI engineering. However, while it presents some interesting findings, it lacks concrete actionable steps for the audience to implement in their own AI-powered product development.","\u002Fsummaries\u002F0620e2900fa5d4a4-small-open-llms-replicate-claude-mythos-bug-hunts-summary","2026-04-18 08:48:05","2026-04-19 01:22:29",{"title":3860,"description":56},{"loc":3919},"0620e2900fa5d4a4","The Decoder","https:\u002F\u002Fthe-decoder.com\u002Fthe-myth-of-claude-mythos-crumbles-as-small-open-models-hunt-the-same-cybersecurity-bugs-anthropic-showcased\u002F","summaries\u002F0620e2900fa5d4a4-small-open-llms-replicate-claude-mythos-bug-hunts-summary",[109,108,107],"Small open models like 3.6B-param GPT-OSS-20b detect and exploit the same cybersecurity bugs as Anthropic's restricted Claude Mythos, proving pipelines—not model size—unlock capabilities.",[],"VBKlihfCzaQlnHh54O5H5Km4j4SoTWDZ3cLdtY20goQ",{"id":3933,"title":3934,"ai":3935,"body":3940,"categories":3981,"created_at":64,"date_modified":64,"description":56,"extension":65,"faq":64,"featured":66,"kicker_label":64,"meta":3982,"navigation":96,"path":3998,"published_at":3999,"question":64,"scraped_at":4000,"seo":4001,"sitemap":4002,"source_id":4003,"source_name":4004,"source_type":103,"source_url":4005,"stem":4006,"tags":4007,"thumbnail_url":64,"tldr":4008,"tweet":64,"unknown_tags":4009,"__hash__":4010},"summaries\u002Fsummaries\u002F137a11ab6b422470-gemma-4-open-source-llms-run-offline-on-phones-summary.md","Gemma 4: Open-Source LLMs Run Offline on Phones",{"provider":7,"model":8,"input_tokens":3936,"output_tokens":3937,"processing_time_ms":3938,"cost_usd":3939},7755,1909,13903,0.002483,{"type":14,"value":3941,"toc":3976},[3942,3946,3949,3952,3956,3959,3962,3966,3973],[17,3943,3945],{"id":3944},"gemma-4-closes-open-source-performance-gap","Gemma 4 Closes Open-Source Performance Gap",[22,3947,3948],{},"Google's Gemma 4 family includes four multimodal models: E2B (effective 2B parameters, fits phones), E4B (effective 4B), 26B MoE (25B total but 4B active for efficiency), and 31B dense flagship. All handle text, images, audio (larger ones add video), offer 256K token context, native function calling via special tokens, and built-in step-by-step reasoning. Apache 2 license enables full commercial use, modification, and fine-tuning without restrictions—unlike prior Gemma versions.",[22,3950,3951],{},"On Arena leaderboard, 31B ranks #27 overall (Elo 1452) but #3 open-source, beating Llama (biggest ecosystem), Qwen (200+ languages), and DeepSeek (top SWE-bench coder). 26B MoE is #6 open-source (Elo 1441) despite 10x smaller active size. Benchmarks show 31B at 89.2% AIME 2026 math (4.3x Gemma 3's 20.8%), 80% LiveCodeBench coding, 84.3% GPQA diamond science. Edge E4B hits 42.5% AIME\u002F52% LiveCodeBench on T4 GPU; E2B gets 37.5% AIME on phones. This shrinks the open-closed gap to ~90% capability for most tasks, making local runs viable over paid APIs.",[17,3953,3955],{"id":3954},"edge-efficiency-enables-new-apps","Edge Efficiency Enables New Apps",[22,3957,3958],{},"E2B runs on \u003C1.5GB RAM (quantized), delivering 133 prefill\u002F7.6 decode tokens\u002Fsec on $80 Raspberry Pi 5 CPU (reads prompts instantly, ~8 words\u002Fsec output). Qualcomm Snapdragon NPU hits 3700 prefill\u002F31 decode—real-time chat speed, 4x faster than Gemma 3 with 60% less battery. No internet, zero data leakage, unlimited use.",[22,3960,3961],{},"Builders already ship: browser vision app with Roboflow RFDeer object detection + Gemma describing scenes as medieval bard via WebGPU\u002Ftransformers.js; Envision accessibility app for blind users (local phone scene description); full local agents browsing web, managing files, executing code, chaining workflows. Run 26B MoE (laptop-friendly) for flagship quality at edge costs.",[17,3963,3965],{"id":3964},"install-locally-and-weigh-trade-offs","Install Locally and Weigh Trade-offs",[22,3967,3968,3969,3972],{},"Use Ollama: download from ollama.com, run ",[3702,3970,3971],{},"ollama pull gemma4:26b"," (6min install). Test in Ollama app—e.g., explains MoE vs dense: dense activates all parameters (cost scales fully); MoE gates to subset experts for larger effective size at lower compute. Integrates with OpenClaw for local agents (web\u002Ffile\u002Fcode tasks). Hugging Face offers browser WebGPU demo, no install.",[22,3974,3975],{},"Limitations: Edge E2B\u002FE4B weak on complex reasoning, deep code, large docs—use 31B or closed models. Quantization (4\u002F2-bit for devices) drops quality below full-precision benchmarks. New release (4 days old) lacks Llama's fine-tunes\u002Fadapters\u002Fecosystem. Video only on 26B\u002F31B. 26 closed models still lead overall; gap shrinks but persists for peak tasks. Ideal for simple\u002Flocal\u002Foffline; pair with closed for heavy lifts.",{"title":56,"searchDepth":57,"depth":57,"links":3977},[3978,3979,3980],{"id":3944,"depth":57,"text":3945},{"id":3954,"depth":57,"text":3955},{"id":3964,"depth":57,"text":3965},[],{"content_references":3983,"triage":3996},[3984,3986,3988,3990,3992,3994],{"type":81,"title":3740,"url":3985,"context":84},"https:\u002F\u002Follama.com\u002Fdownload",{"type":81,"title":3987,"context":84},"Hugging Face",{"type":81,"title":3989,"context":84},"Roboflow RFDeer",{"type":88,"title":3991,"context":73},"Arena AI leaderboard",{"type":88,"title":3993,"context":73},"AIME 2026 math benchmark",{"type":81,"title":3995,"context":84},"transformers.js",{"relevance":93,"novelty":3744,"quality":93,"actionability":93,"composite":3745,"reasoning":3997},"Category: AI & LLMs. The article discusses the capabilities of the Gemma 4 models, which are relevant to AI product builders looking to implement open-source LLMs in their applications. It provides practical insights on local deployment and performance benchmarks, addressing the audience's need for actionable information on AI tools.","\u002Fsummaries\u002F137a11ab6b422470-gemma-4-open-source-llms-run-offline-on-phones-summary","2026-04-12 16:41:13","2026-04-19 03:29:20",{"title":3934,"description":56},{"loc":3998},"137a11ab6b422470","Nick Puru | AI Automation","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=i5qw6DsxUug","summaries\u002F137a11ab6b422470-gemma-4-open-source-llms-run-offline-on-phones-summary",[109,108,107],"Google's Gemma 4 family delivers frontier-quality AI locally on phones and $80 Raspberry Pis under Apache 2 license, ranking #3 among open models (Elo 1452) with 4.3x math gains, slashing API costs and vendor lock-in.",[],"aB24r0P5RWM4eZ5rnKCwotNn4vZ18sddrSOC2S4H14A"]