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
-
stepfun-ai/Step-3.5-Flash · 2026-10-14 06:02:59.948544 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 632 475.2 Providers[1] · Throughput 26.8505004916901 21.81784361704098 -
meta-llama/Llama-Guard-4-12B · 2026-10-14 06:02:59.928365 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 329.8 396 Providers[0] · Throughput 7.46917728856472 8.25511436096636 -
google/gemma-4-26B-A4B-it · 2026-10-14 06:02:59.909874 UTC
Current Model ListingHugging Face
6 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 768.2 446.8 Providers[0] · Throughput 169.67322367942933 58.145539902951086 Providers[2] · First Token Latency Ms 391.4 381.4 Providers[2] · Throughput 190.65473943757934 164.40816035486571 Providers[3] · First Token Latency Ms 616.8 529.2 -
Qwen/Qwen3.5-122B-A10B · 2026-10-14 06:02:59.891811 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 983.8 814.2 Providers[0] · Throughput 117.96606191373398 108.46414862203169 Providers[1] · First Token Latency Ms 267.2 317.2 Providers[1] · Throughput 47.831946478034006 40.762857462445446 -
ibm-granite/granite-4.2-30b · 2026-10-14 06:02:59.872218 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2186 4175 Providers[0] · Throughput 61.04633416763323 58.613211417853584 -
zai-org/GLM-5.2 · 2026-10-14 06:02:59.853805 UTC
Current Model ListingHugging Face
12 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1302.8 1849.4 Providers[0] · Throughput 65.98340148406737 53.41256498916558 Providers[1] · First Token Latency Ms 211.8 253 Providers[1] · Throughput 98.7126412737205 105.59892248930441 Providers[3] · First Token Latency Ms 2410.6666666666665 2862 -
Qwen/Qwen3-VL-30B-A3B-Instruct · 2026-10-14 06:02:59.833949 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 772 1014 Providers[0] · Throughput 36.336947152025836 23.64141330169793 Providers[2] · First Token Latency Ms 280.2 302.2 Providers[2] · Throughput 28.974245242582914 33.271994439709 -
tencent/Hy4-preview · 2026-10-14 06:02:59.815445 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 2343 3610 Providers[0] · Throughput 36.27137011307924 27.83507888507534 Providers[1] · First Token Latency Ms 656.6 623.4 Providers[1] · Throughput 42.44419059642956 11.860306436674389 -
stepfun-ai/Step-3.7-Flash · 2026-10-14 06:02:59.791407 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 366.5 1136.8 Providers[1] · Throughput 11.500886218212159 14.612675834216759 -
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · 2026-10-14 06:02:59.756249 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 441.6 641.5 Providers[0] · Supports Structured Output True False Providers[0] · Throughput 57.7473806022601 34.07437536957789 -
Qwen/Qwen3.6-27B · 2026-10-14 06:02:59.742256 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 444.2 1719 Providers[1] · Throughput 66.92870012433096 57.06621694132673 Providers[2] · First Token Latency Ms 217 260.6 Providers[2] · Throughput 74.84223892043414 74.08884424546227 -
inclusionAI/Ling-3.0-flash-VL · 2026-10-14 06:02:59.724487 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 986.8 909.8 Providers[0] · Throughput 232.32772594961648 244.12611947203158 -
deepseek-ai/DeepSeek-V4-Pro · 2026-10-14 06:02:59.707113 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 637.4 725.4 Providers[0] · Throughput 72.46837676037117 47.0025013779922 Providers[2] · First Token Latency Ms 504 345.2 Providers[2] · Throughput 42.27454743298101 51.252233618788964 -
tencent/Hy3 · 2026-10-14 06:02:59.679468 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 573.8 872.2 Providers[1] · Throughput 37.37733670203213 28.737069191233594 -
zai-org/GLM-4.5V · 2026-10-14 06:02:59.660265 UTC
Current Model ListingHugging Face
4 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 887.4 989.2 Providers[0] · Throughput 71.39473109270833 57.4425054393325 Providers[1] · First Token Latency Ms 2017.8 2698.8 Providers[1] · Throughput 59.31219541292761 36.996144787601736 -
CohereLabs/command-a-vision-07-2025 · 2026-10-14 06:02:59.638651 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 154.5 181.5 Providers[0] · Throughput 46.066604499279876 47.039233018764335 -
aisingapore/Gemma-SEA-LION-v4-27B-IT · 2026-10-14 06:02:59.618752 UTC
Current Model ListingHugging Face
3 Changed Fields
Field / Array Position Previous Value Observed Value Providers[1] · First Token Latency Ms 1245.2 1613.6 Providers[1] · Supports Structured Output True False Providers[1] · Throughput 50.52512702304939 46.365926934010346 -
ibm-granite/granite-4.2-8b · 2026-10-14 06:02:59.597550 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 302.4 197.2 Providers[0] · Throughput 142.50566884726567 150.33727482591564 -
CohereLabs/command-a-plus-05-2026-w4a4 · 2026-10-14 06:02:59.577975 UTC
Current Model ListingHugging Face
2 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 293.6 184.2 Providers[0] · Throughput 163.61848471079207 140.94036709075937 -
Qwen/Qwen3.8-27B · 2026-10-14 06:02:59.557684 UTC
Current Model ListingHugging Face
38 Changed Fields
Field / Array Position Previous Value Observed Value Providers[0] · First Token Latency Ms 1346.2 941.4 Providers[0] · Throughput 31.9486320107463 30.201297482593354 Providers[1] · Provider featherless-ai cerebras Providers[2] · Context Length 262144 Not Reported Providers[2] · First Token Latency Ms 414.75 Not Reported - Next 20 Changes →