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
-
speakleash/Bielik-11B-v3.0-Instruct · 2026-10-13 12:01:10.927656 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1019.2 975.4 Providers[0] · Throughput 54.807042263341614 55.572865665427386 -
MiniMaxAI/MiniMax-M3 · 2026-10-13 12:01:10.915881 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1043.4 884.6 Providers[0] · Throughput 89.65386210248025 72.53277697313348 Providers[1] · First Token Latency Ms 362.4 327.6 Providers[1] · Throughput 65.3090603428466 42.78203700487718 Providers[2] · First Token Latency Ms 691.2 902.8 -
CohereLabs/command-a-reasoning-08-2025 · 2026-10-13 12:01:10.903734 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 213.6 205.6 Providers[0] · Throughput 99.1995292268476 105.23348722221435 -
Qwen/Qwen3-14B · 2026-10-13 12:01:10.889880 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 234.2 193.6 Providers[1] · Throughput 16.038863938066406 68.95524898841963 -
zai-org/GLM-4.6V-FP8 · 2026-10-13 12:01:10.876591 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 3120.8 2521.8 Providers[0] · Throughput 35.026035621658444 55.40642221693914 -
openai/gpt-oss-safeguard-20b · 2026-10-13 12:01:10.864134 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 223.6 114.4 Providers[0] · Throughput 785.9725944760405 845.8838113899228 -
Qwen/Qwen3-30B-A3B · 2026-10-13 12:01:10.852828 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 520.4 214.6 Providers[0] · Supports Structured Output True False Providers[0] · Throughput 90.04664860628527 96.83393946193948 -
openai/gpt-oss-120b · 2026-10-13 12:01:10.838373 UTC
Current Model ListingHugging Face
17 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 331.4 648.2 Providers[0] · Throughput 430.02239943080974 389.1689417922172 Providers[2] · First Token Latency Ms 344.8 272 Providers[2] · Throughput 881.3391089830924 1031.9330639557775 Providers[3] · First Token Latency Ms 192 220.6 -
google/gemma-3-4b-it · 2026-10-13 12:01:10.824945 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 655 475.4 Providers[1] · Throughput 17.017700969513307 33.02224609644029 -
Qwen/Qwen3-235B-A22B-Thinking-2507 · 2026-10-13 12:01:10.808216 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 893.2 455.4 Providers[1] · Throughput 34.677314919069815 161.36911465572598 -
Qwen/Qwen3.8-2.4T-A95B · 2026-10-13 12:01:10.796653 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1515 1202.6 Providers[0] · Throughput 31.57666851769192 35.164607340410456 Providers[1] · First Token Latency Ms 615.4 423.6 Providers[1] · Throughput 64.25552134272908 123.2819978387819 Providers[2] · First Token Latency Ms 871.6 670.6 -
CohereLabs/command-a-translate-08-2025 · 2026-10-13 12:01:10.785084 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 239.6 333.2 Providers[0] · Throughput 70.40451348103154 70.46511603495792 -
zai-org/GLM-4.6V-Flash · 2026-10-13 12:01:10.772780 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 959.4 944.4 Providers[0] · Throughput 34.02169375555879 74.10926234543935 -
zai-org/GLM-5 · 2026-10-13 12:01:10.758024 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1239.2 1668.75 Providers[0] · Throughput 40.91901691617743 39.90811473974662 Providers[3] · First Token Latency Ms 308 362.6 Providers[3] · Throughput 82.5374839564391 58.12796283323219 -
deepseek-ai/DeepSeek-V4.1-Flash · 2026-10-13 12:01:10.745931 UTC
Current Model ListingHugging Face
22 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 4027 4610 Providers[0] · Throughput 68.20351930159596 61.40620202640467 Providers[1] · First Token Latency Ms 953 801.6 Providers[1] · Throughput 78.35260949756601 74.58750186712163 Providers[3] · First Token Latency Ms 4768 507.2 -
Sao10K/L3-8B-Stheno-v3.2 · 2026-10-13 12:01:10.731302 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 678.4 594.75 Providers[0] · Throughput 107.65110009726043 116.57784969716703 -
moonshotai/Kimi-K2-Instruct · 2026-10-13 12:01:10.709783 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1288 1086.2 Providers[0] · Throughput 46.92590949789954 51.45609848097119 -
Qwen/Qwen3.6-35B-A3B · 2026-10-13 12:01:10.698143 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 566.2 840.2 Providers[1] · Throughput 169.04041823301537 27.054168734533487 Providers[2] · First Token Latency Ms 277.4 275 Providers[2] · Throughput 39.39955957639794 116.40582505332786 -
Qwen/Qwen2.5-72B-Instruct · 2026-10-13 12:01:10.683360 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 335 501.6 Providers[1] · Throughput 42.53270195402315 46.93986920437157 -
prism-ml/Ternary-Bonsai-27B-AWQ-4bit · 2026-10-13 12:01:10.664393 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 302.4 348 Providers[0] · Throughput 45.3880932982423 24.789905550459853 - Next 20 Changes →