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
-
zai-org/AutoGLM-Phone-9B-Multilingual · 2026-10-14 18:05:10.756667 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 675.8 913.6 Providers[0] · Throughput 79.4038135971766 88.18972062941914 -
CohereLabs/aya-expanse-32b · 2026-10-14 18:05:10.727180 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 177 173.4 Providers[0] · Throughput 47.939760696633655 40.997309680156675 -
XiaomiMiMo/MiMo-V2.5-Pro · 2026-10-14 18:05:10.709655 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1491.4 2542 Providers[0] · Throughput 19.749038021158043 22.759361152027743 Providers[1] · First Token Latency Ms 919 1312.25 Providers[1] · Throughput 17.9722113681314 14.472321780627768 -
Qwen/Qwen3-Next-80B-A3B-Instruct · 2026-10-14 18:05:10.697562 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 490.2 429.8 Providers[1] · Throughput 39.308858611978465 77.97357508559824 -
CohereLabs/c4ai-command-r7b-12-2024 · 2026-10-14 18:05:10.684663 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 163.6 214.2 Providers[0] · Throughput 76.9471231597988 73.76311604777882 -
zai-org/GLM-5.3-Flash · 2026-10-14 18:05:10.670796 UTC
Current Model ListingHugging Face
23 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1649.8 1350 Providers[0] · Throughput 39.49177828574075 67.89592454700785 Providers[1] · First Token Latency Ms 129 177.2 Providers[1] · Throughput 138.24943225517262 89.5310022821308 Providers[2] · First Token Latency Ms 613.4 957.2 -
aisingapore/Qwen-SEA-LION-v4-32B-IT · 2026-10-14 18:05:10.654714 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 4988 1283.5 Providers[1] · Throughput 31.837606837606835 37.867083428575945 -
moonshotai/Kimi-K2.6 · 2026-10-14 18:05:10.640750 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1728.8 1953.4 Providers[0] · Throughput 31.023928260888255 33.71864951710654 Providers[2] · First Token Latency Ms 1228.6 891.4 Providers[2] · Throughput 6.245176195251344 11.053923992878987 -
ibm-granite/granite-4.2-3b · 2026-10-14 18:05:10.625350 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 202.8 215 Providers[0] · Throughput 235.17710564261455 230.3108932319115 -
prism-ml/Ternary-Bonsai-27B-gguf · 2026-10-14 18:05:10.605674 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1821.6 484.6 Providers[0] · Throughput 30.140108870680564 60.72142714037276 -
zai-org/GLM-5.3 · 2026-10-14 18:05:10.594532 UTC
Current Model ListingHugging Face
12 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1118.6 1190.6 Providers[0] · Throughput 71.07351937555407 62.82371219512676 Providers[1] · First Token Latency Ms 505.6 500.4 Providers[1] · Throughput 65.33162634647336 59.990965027369825 Providers[2] · First Token Latency Ms 524.2 1051 -
inclusionAI/Ling-3.0-flash · 2026-10-14 18:05:10.582114 UTC
Current Model ListingHugging Face
15 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 885.2 799 Providers[0] · Throughput 154.44615607723196 189.1836662105446 Providers[1] · @item Type 5 Not Reported Providers[1] · Context Length 131072 Not Reported Providers[1] · First Token Latency Ms 422.6 Not Reported -
CohereLabs/command-a-plus-05-2026-fp8 · 2026-10-14 18:05:10.568157 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 286.6 205.4 Providers[0] · Throughput 97.23683546895897 80.77208946233763 -
openai/gpt-oss-20b · 2026-10-14 18:05:10.554662 UTC
Current Model ListingHugging Face
7 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 238.4 387 Providers[0] · Throughput 694.3548305979903 616.0736705317083 Providers[2] · First Token Latency Ms 216.8 512 Providers[2] · Supports Structured Output True False Providers[2] · Throughput 61.55100830951113 67.29475100942128 -
Qwen/Qwen3.5-35B-A3B · 2026-10-14 18:05:10.543998 UTC
Current Model ListingHugging Face
15 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 992 981.8 Providers[0] · Throughput 74.80872143083184 72.71772782410255 Providers[1] · @item Type 5 Not Reported Providers[1] · Context Length 262144 Not Reported Providers[1] · First Token Latency Ms 180 Not Reported -
deepseek-ai/DeepSeek-V3-0324 · 2026-10-14 18:05:10.531742 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 267 414.6 Providers[1] · Throughput 70.4651652713188 47.87990881956691 -
google/gemma-4-31B-it · 2026-10-14 18:05:10.518688 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 645.5 2409 Providers[0] · Throughput 25.628140852052063 21.913842160435284 Providers[2] · First Token Latency Ms 731.6 1412.4 Providers[2] · Throughput 23.232200909332157 27.85110826517832 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · 2026-10-14 18:05:10.495144 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 904 2663 Providers[0] · Throughput 50.62524820665688 30.571203792249058 -
MiniMaxAI/MiniMax-M2.7 · 2026-10-14 18:05:10.479615 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1275 1178.2 Providers[0] · Throughput 38.97422409013974 44.24723595939618 Providers[2] · First Token Latency Ms 621 456.2 Providers[2] · Throughput 14.886320425012888 34.770560183375025 -
meta-llama/Llama-3.3-70B-Instruct · 2026-10-14 18:05:10.463543 UTC
Current Model ListingHugging Face
8 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 403 796.2 Providers[0] · Throughput 50.582285106778194 33.35201699181461 Providers[1] · First Token Latency Ms 275 372.2 Providers[1] · Throughput 102.66108334459004 81.54384078877843 Providers[3] · First Token Latency Ms 493.6 501.8 - Next 20 Changes →