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
-
CohereLabs/aya-expanse-32b · 2026-10-13 18:02:54.775622 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 255.8 294.2 Providers[0] · Throughput 46.40211431114236 43.947203293111826 -
XiaomiMiMo/MiMo-V2.5-Pro · 2026-10-13 18:02:54.753453 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2041.4 1470.2 Providers[0] · Throughput 25.55507655049783 24.96418027632002 Providers[1] · First Token Latency Ms 817.5 654.2 Providers[1] · Throughput 17.933113023597734 21.4276780592057 -
Qwen/Qwen3-Next-80B-A3B-Instruct · 2026-10-13 18:02:54.722237 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 1510.4 482.4 Providers[1] · Throughput 72.44648151316804 63.62464539091919 -
CohereLabs/c4ai-command-r7b-12-2024 · 2026-10-13 18:02:54.699765 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 232 212.4 Providers[0] · Throughput 71.89195906681057 75.24264905631033 -
zai-org/GLM-5.3-Flash · 2026-10-13 18:02:54.677256 UTC
Current Model ListingHugging Face
10 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1479.75 1772.8 Providers[0] · Throughput 44.900662835971744 54.72385200274056 Providers[1] · First Token Latency Ms 206 220.4 Providers[1] · Throughput 100.58900844153777 118.36820625112568 Providers[2] · First Token Latency Ms 471.6 4701 -
aisingapore/Qwen-SEA-LION-v4-32B-IT · 2026-10-13 18:02:54.649495 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 905.75 1248.6 Providers[1] · Throughput 42.823159952851185 40.790462579881876 -
moonshotai/Kimi-K2.6 · 2026-10-13 18:02:54.625464 UTC
Current Model ListingHugging Face
15 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1882.4 1419.6 Providers[0] · Throughput 32.20718906854662 33.43065276272709 Providers[2] · @item Type Not Reported 5 Providers[2] · Context Length Not Reported 262144 Providers[2] · First Token Latency Ms Not Reported 1153 -
ibm-granite/granite-4.2-3b · 2026-10-13 18:02:54.597349 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 236.6 479.8 Providers[0] · Throughput 226.83034287221798 192.19190816269446 -
prism-ml/Ternary-Bonsai-27B-gguf · 2026-10-13 18:02:54.576593 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 345.2 322.6 Providers[0] · Throughput 47.28262198376803 51.823491802811404 -
zai-org/GLM-5.3 · 2026-10-13 18:02:54.556799 UTC
Current Model ListingHugging Face
12 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 968.8 996.2 Providers[0] · Throughput 60.01976148144682 59.88459784398034 Providers[1] · First Token Latency Ms 257.2 250.2 Providers[1] · Throughput 113.04239412575718 100.86927615402655 Providers[2] · First Token Latency Ms 586.4 507 -
inclusionAI/Ling-3.0-flash · 2026-10-13 18:02:54.527100 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 921 761.2 Providers[0] · Throughput 260.0930273372604 245.1866552394576 Providers[1] · First Token Latency Ms 370.6666666666667 413.6 Providers[1] · Throughput 26.091401786219205 23.71545421643222 -
CohereLabs/command-a-plus-05-2026-fp8 · 2026-10-13 18:02:54.506845 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 317.8 220 Providers[0] · Throughput 100.92660609385982 141.63336466351947 -
openai/gpt-oss-20b · 2026-10-13 18:02:54.480933 UTC
Current Model ListingHugging Face
7 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 185.4 241.4 Providers[0] · Throughput 774.4717409221805 751.6355579719537 Providers[2] · First Token Latency Ms 350.8 317.4 Providers[2] · Supports Structured Output True False Providers[2] · Throughput 52.43544757612985 53.1630475921278 -
Qwen/Qwen3.5-35B-A3B · 2026-10-13 18:02:54.460980 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 847.2 879 Providers[0] · Throughput 74.7220253614989 79.02107302994129 Providers[1] · First Token Latency Ms 187 170 Providers[1] · Throughput 129.2971599084636 88.38608223092153 -
deepseek-ai/DeepSeek-V3-0324 · 2026-10-13 18:02:54.438136 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 454.6 884.8 Providers[1] · Throughput 58.60448854193815 43.77061031786331 -
google/gemma-4-31B-it · 2026-10-13 18:02:54.412794 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 988 4733 Providers[0] · Throughput 34.965100069262206 26.07759984809165 Providers[2] · First Token Latency Ms 476.6 476.8 Providers[2] · Throughput 24.665912405589047 29.835640366951953 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · 2026-10-13 18:02:54.393323 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 501 441.6 Providers[0] · Throughput 84.2297416515617 50.08493923482971 -
MiniMaxAI/MiniMax-M2.7 · 2026-10-13 18:02:54.367910 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1618.2 1163.8 Providers[0] · Throughput 30.110745890320594 46.545737205627425 Providers[2] · First Token Latency Ms 792.4 838.8 Providers[2] · Throughput 9.057859549320805 11.468902190710335 -
meta-llama/Llama-3.3-70B-Instruct · 2026-10-13 18:02:54.348363 UTC
Current Model ListingHugging Face
9 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 478.8 622.6 Providers[0] · Throughput 48.081527287049724 40.17253462491311 Providers[1] · First Token Latency Ms 797.8 551.8 Providers[1] · Throughput 53.0181395231582 89.01855239470646 Providers[3] · First Token Latency Ms 515.6 461.4 -
thinkingmachines/Inkling-Small · 2026-10-13 18:02:54.325797 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1111.4 415 Providers[0] · Throughput 27.04200418954607 115.8199832250554 - Next 20 Changes →