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
-
Qwen/Qwen3-30B-A3B · 2026-10-14 18:05:09.739174 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 213 256.6 Providers[0] · Supports Structured Output True False Providers[0] · Throughput 126.3354316857066 102.55832557425484 -
openai/gpt-oss-120b · 2026-10-14 18:05:09.721252 UTC
Current Model ListingHugging Face
19 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 266.2 373.4 Providers[0] · Throughput 423.39355984212835 394.80789661868573 Providers[1] · First Token Latency Ms 941.2 458.2 Providers[1] · Throughput 125.33785510629238 164.56762740362655 Providers[2] · First Token Latency Ms 193.6 392.6 -
google/gemma-3-4b-it · 2026-10-14 18:05:09.704549 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 307.4 383.8 Providers[1] · Supports Structured Output False True Providers[1] · Throughput 56.16314634360517 25.504700501027017 -
Qwen/Qwen3-235B-A22B-Thinking-2507 · 2026-10-14 18:05:09.689375 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 1161 2040.5 Providers[1] · Throughput 27.562636090515696 10.157749982069193 -
Qwen/Qwen3.8-2.4T-A95B · 2026-10-14 18:05:09.674369 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1387.2 1637.4 Providers[0] · Throughput 27.831103355206295 32.1010683384677 Providers[1] · First Token Latency Ms 570.2 801.2 Providers[1] · Throughput 77.95221446173059 64.68911082439482 Providers[2] · First Token Latency Ms 644.2 850 -
CohereLabs/command-a-translate-08-2025 · 2026-10-14 18:05:09.661034 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 285.8 325.2 Providers[0] · Throughput 70.10155679554722 70.60320980678989 -
zai-org/GLM-4.6V-Flash · 2026-10-14 18:05:09.645484 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1420 1499.6 Providers[0] · Throughput 37.81813324479536 25.386482061855478 -
zai-org/GLM-5 · 2026-10-14 18:05:09.634161 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1490 1867.4 Providers[0] · Throughput 50.72829020991057 50.13779705892157 Providers[3] · First Token Latency Ms 1742.6 606.2 Providers[3] · Throughput 30.329058260237694 54.12691186516339 -
deepseek-ai/DeepSeek-V4.1-Flash · 2026-10-14 18:05:09.618016 UTC
Current Model ListingHugging Face
6 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 833.6 871.5 Providers[1] · Throughput 70.61197395948037 50.44684152988522 Providers[3] · First Token Latency Ms 338.8 4282 Providers[3] · Throughput 146.57355533913457 96.62769349695623 Providers[4] · First Token Latency Ms 379.8 584.4 -
Sao10K/L3-8B-Stheno-v3.2 · 2026-10-14 18:05:09.603911 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 479.8 485.2 Providers[0] · Throughput 108.14319434572697 105.59702944986842 -
CohereLabs/c4ai-command-a-03-2025 · 2026-10-14 18:05:09.587591 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 256 246.8 Providers[0] · Throughput 45.762804203502704 49.43849151532908 -
moonshotai/Kimi-K2-Instruct · 2026-10-14 18:05:09.512367 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1760.6 1387 Providers[0] · Throughput 51.020092769995856 35.83877943259481 -
Qwen/Qwen3.6-35B-A3B · 2026-10-14 18:05:09.500106 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 828.2 1098.8 Providers[1] · Throughput 42.64678426277359 29.113511137248548 Providers[2] · First Token Latency Ms 762.5 249 Providers[2] · Throughput 20.933626524288353 12.926409948165096 -
Qwen/Qwen2.5-72B-Instruct · 2026-10-14 18:05:09.486772 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 292.8 433.4 Providers[1] · Throughput 27.298852180985442 24.780842513578914 -
CohereLabs/tiny-aya-global · 2026-10-14 18:05:09.474468 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 155.4 160 Providers[0] · Throughput 134.04299622554686 133.88998523082674 -
prism-ml/Ternary-Bonsai-27B-AWQ-4bit · 2026-10-14 18:05:09.462633 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 347 322.2 Providers[0] · Throughput 46.17076351979053 75.12616671078291 -
CohereLabs/tiny-aya-fire · 2026-10-14 18:05:09.452885 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 166.2 165 Providers[0] · Throughput 133.51329573072599 133.6810939508981 -
CohereLabs/c4ai-command-r-08-2024 · 2026-10-14 18:05:09.442054 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 181.8 1120 Providers[0] · Throughput 51.3024252203864 38.92536513466435 -
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · 2026-10-14 18:05:09.428967 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 538.8 445.8 Providers[0] · Throughput 258.3972452231828 246.63764647599527 -
Qwen/Qwen3-235B-A22B-Instruct-2507 · 2026-10-14 18:05:09.414467 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 493.6 627.6 Providers[0] · Throughput 33.49485889073213 55.3264380049093 Providers[1] · First Token Latency Ms 823.2 233.4 Providers[1] · Throughput 15.893060216051833 19.575197155530766 - Next 20 Changes →