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/GLM-4.6V-Flash · 2026-10-14 12:03:02.281246 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1128.2 1420 Providers[0] · Throughput 46.981460755780645 37.81813324479536 -
zai-org/GLM-5 · 2026-10-14 12:03:02.270289 UTC
Current Model ListingHugging Face
6 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1893 1490 Providers[0] · Throughput 52.808867128857784 50.72829020991057 Providers[2] · First Token Latency Ms 3042 3437 Providers[2] · Throughput 74.74474888454138 70.08690776562938 Providers[3] · First Token Latency Ms 459.6 1742.6 -
deepseek-ai/DeepSeek-V4.1-Flash · 2026-10-14 12:03:02.258228 UTC
Current Model ListingHugging Face
6 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 1303.8 833.6 Providers[1] · Throughput 88.21207282991612 70.61197395948037 Providers[3] · First Token Latency Ms 4121 338.8 Providers[3] · Throughput 43.122035360069 146.57355533913457 Providers[4] · First Token Latency Ms 449 379.8 -
Sao10K/L3-8B-Stheno-v3.2 · 2026-10-14 12:03:02.246120 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 650.8 479.8 Providers[0] · Throughput 107.05771583058274 108.14319434572697 -
CohereLabs/c4ai-command-a-03-2025 · 2026-10-14 12:03:02.234950 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 230.8 256 Providers[0] · Throughput 51.55522162656538 45.762804203502704 -
moonshotai/Kimi-K2-Instruct · 2026-10-14 12:03:02.222740 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1863.4 1760.6 Providers[0] · Throughput 44.340155548221844 51.020092769995856 -
Qwen/Qwen3.6-35B-A3B · 2026-10-14 12:03:02.208643 UTC
Current Model ListingHugging Face
5 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 454.6 828.2 Providers[1] · Throughput 168.57029684704452 42.64678426277359 Providers[2] · First Token Latency Ms 1867 762.5 Providers[2] · Supports Structured Output False True Providers[2] · Throughput 6.551062254744608 20.933626524288353 -
CohereLabs/tiny-aya-global · 2026-10-14 12:03:02.188209 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 159.4 155.4 Providers[0] · Throughput 134.03279703116442 134.04299622554686 -
prism-ml/Ternary-Bonsai-27B-AWQ-4bit · 2026-10-14 12:03:02.169274 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 410.4 347 Providers[0] · Throughput 46.48176649018099 46.17076351979053 -
CohereLabs/tiny-aya-fire · 2026-10-14 12:03:02.157743 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 161 166.2 Providers[0] · Throughput 133.37762616995576 133.51329573072599 -
CohereLabs/c4ai-command-r-08-2024 · 2026-10-14 12:03:02.141080 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 377.4 181.8 Providers[0] · Throughput 36.073609270523185 51.3024252203864 -
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · 2026-10-14 12:03:02.128278 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 391.2 538.8 Providers[0] · Throughput 144.90346726361992 258.3972452231828 -
Qwen/Qwen3-235B-A22B-Instruct-2507 · 2026-10-14 12:03:02.117092 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 328.4 493.6 Providers[0] · Throughput 82.8203579331601 33.49485889073213 Providers[1] · First Token Latency Ms 320.6 823.2 Providers[1] · Throughput 25.380688958192174 15.893060216051833 -
MiniMaxAI/MiniMax-M1-80k · 2026-10-14 12:03:02.106294 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2167.8 1197.8 Providers[0] · Throughput 33.97229676017746 42.643473457203186 -
zai-org/GLM-4.5V-FP8 · 2026-10-14 12:03:02.092978 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1823 2821 Providers[0] · Throughput 62.715584822828475 39.16507400719324 -
deepseek-ai/DeepSeek-V4-Flash-0731 · 2026-10-14 12:03:02.078760 UTC
Current Model ListingHugging Face
10 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 799.4 698.2 Providers[0] · Throughput 93.16851956797979 79.14509166032732 Providers[1] · First Token Latency Ms 1170.2 650.4 Providers[1] · Throughput 23.65198235709959 54.83670514123448 Providers[3] · First Token Latency Ms 574.2 1036.8 -
meta-llama/Llama-4-Scout-17B-16E-Instruct · 2026-10-14 12:03:02.064584 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 535.2 1149.4 Providers[0] · Throughput 32.91030795403176 31.790107659477393 Providers[1] · First Token Latency Ms 3383.6 383.8 Providers[1] · Throughput 24.169984202248475 41.18140411890423 -
deepseek-ai/DeepSeek-R1-0528 · 2026-10-14 12:03:02.051714 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1303 1035.2 Providers[0] · Throughput 26.553164202831717 25.40358376889761 Providers[2] · First Token Latency Ms 659 522 Providers[2] · Throughput 20.484572136932393 28.145280215598326 -
zai-org/GLM-4.7 · 2026-10-14 12:03:02.039887 UTC
Current Model ListingHugging Face
24 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 3391.2 3674.8 Providers[0] · Throughput 26.431700133952507 23.246865865125148 Providers[2] · First Token Latency Ms 3079.5 1042 Providers[2] · Is Model Author True False Providers[2] · Provider zai-org deepinfra -
meta-llama/Llama-3.1-8B-Instruct · 2026-10-14 12:03:02.028622 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1540 469.6 Providers[0] · Throughput 148.56867677020654 155.33686449676316 Providers[2] · First Token Latency Ms 474 363.8 Providers[2] · Throughput 34.939482022955154 32.5061872867269 - Next 20 Changes →