Catalog Changes
Version history starts when recording is enabled. Versions are created when reported values, array items or listing availability change. Array differences align positions, not inferred identities. The first observation is a baseline; unchanged downloads update last observation time.
Catalog Changes
-
moonshotai/Kimi-K2.7-Code · 2026-10-14 12:03:02.542314 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1148 1585 Providers[0] · Throughput 61.86352377996916 35.987887661186825 Providers[2] · First Token Latency Ms 520.4 702.4 Providers[2] · Throughput 24.497674727706347 28.68715989614848 -
CohereLabs/command-a-plus-05-2026-bf16 · 2026-10-14 12:03:02.531095 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 304.2 228 Providers[0] · Throughput 105.39229908841392 110.71263529727226 -
google/gemma-3-12b-it · 2026-10-14 12:03:02.517155 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 393.4 209.8 Providers[1] · Throughput 68.31355296617797 31.87982447673064 -
zai-org/GLM-4.5-Air · 2026-10-14 12:03:02.502349 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 881.2 563.2 Providers[0] · Throughput 76.0364972087617 82.08126995956431 Providers[1] · First Token Latency Ms 1710.8 1596.4 Providers[1] · Throughput 84.15286827364051 83.06622360685733 -
Qwen/Qwen3.5-397B-A17B · 2026-10-14 12:03:02.490236 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1216.4 1113.4 Providers[0] · Throughput 57.16794908724194 57.41845874788777 Providers[2] · First Token Latency Ms 388.6 380.2 Providers[2] · Throughput 112.14059228785341 110.42067198471776 Providers[3] · First Token Latency Ms 450.8 783.4 -
Qwen/Qwen3-32B · 2026-10-14 12:03:02.469155 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 367.8 190.6 Providers[1] · Throughput 30.14654494319469 23.751549734153354 -
zai-org/GLM-4.6 · 2026-10-14 12:03:02.457493 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 3500.6666666666665 3964.75 Providers[0] · Throughput 25.811480377070655 24.979908986879877 Providers[2] · First Token Latency Ms 522.4 426.4 Providers[2] · Throughput 18.022189676657796 63.21678320604993 -
Qwen/Qwen3-Coder-30B-A3B-Instruct · 2026-10-14 12:03:02.445928 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 359.6 325.4 Providers[1] · Throughput 138.8515533707453 131.17419003892041 -
speakleash/Bielik-11B-v3.0-Instruct · 2026-10-14 12:03:02.427588 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 855.8 1537.6 Providers[0] · Throughput 53.07906058197996 53.15666459965526 -
MiniMaxAI/MiniMax-M3 · 2026-10-14 12:03:02.415457 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1410.8 1088.8 Providers[0] · Throughput 92.97140116489572 70.2611017352477 Providers[1] · First Token Latency Ms 1387.6 455.4 Providers[1] · Throughput 42.74297031499128 55.60551534917064 Providers[2] · First Token Latency Ms 715.6 808.4 -
CohereLabs/command-a-reasoning-08-2025 · 2026-10-14 12:03:02.401999 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 206.2 194.8 Providers[0] · Throughput 104.40388603480963 104.08200185846167 -
Qwen/Qwen3-14B · 2026-10-14 12:03:02.388133 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 365.4 187.6 Providers[1] · Throughput 60.00867385661142 54.73519956817722 -
zai-org/GLM-4.6V-FP8 · 2026-10-14 12:03:02.377577 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2363.6 2573 Providers[0] · Throughput 57.42825516320173 33.90001226416561 -
openai/gpt-oss-safeguard-20b · 2026-10-14 12:03:02.366482 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 261.4 182.6 Providers[0] · Throughput 814.2390991841378 806.5329851739972 -
Qwen/Qwen3-30B-A3B · 2026-10-14 12:03:02.354154 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 310.8 213 Providers[0] · Supports Structured Output False True Providers[0] · Throughput 68.94048918163855 126.3354316857066 -
openai/gpt-oss-120b · 2026-10-14 12:03:02.342412 UTC
Current Model ListingHugging Face
20 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 201 266.2 Providers[0] · Throughput 435.1983412406345 423.39355984212835 Providers[1] · First Token Latency Ms 492 941.2 Providers[1] · Supports Structured Output False True Providers[1] · Throughput 189.13880921722426 125.33785510629238 -
google/gemma-3-4b-it · 2026-10-14 12:03:02.330977 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 410.6 307.4 Providers[1] · Supports Structured Output True False Providers[1] · Throughput 43.39622570312193 56.16314634360517 -
Qwen/Qwen3-235B-A22B-Thinking-2507 · 2026-10-14 12:03:02.319363 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 680.2 1161 Providers[1] · Throughput 49.14875893010304 27.562636090515696 @listed 0 1 -
Qwen/Qwen3.8-2.4T-A95B · 2026-10-14 12:03:02.308413 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1383 1387.2 Providers[0] · Throughput 36.025725556060245 27.831103355206295 Providers[1] · First Token Latency Ms 387 570.2 Providers[1] · Throughput 131.94099502060243 77.95221446173059 Providers[2] · First Token Latency Ms 1056.6 644.2 -
CohereLabs/command-a-translate-08-2025 · 2026-10-14 12:03:02.297527 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 517.2 285.8 Providers[0] · Throughput 70.22308728582863 70.10155679554722 - Next 20 Changes →