AImodelsComparison.com 1,086 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
1,086 models · 1,086 open weights · 200 API-only · refreshed nightly

Open-weights models

Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.

Type
All 1,286 Open weights (self-host) 1,086 API-only 200
Task
All text-generation 461 text-to-image 150 image-text-to-text 101 ASR 83 sentence-similarity 56 translation 46 feature-extraction 44 text-classification 43 image-classification 36 token-classification 17 text-to-speech 17 audio-classification 9 image-segmentation 8 object-detection 7 summarization 6 audio-text-to-text 1 any-to-any 1
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
461 models
#ModelParamsContextCommercial use30dMin VRAM
401 Mistral-Nemo-Instruct-2407 mistralai · text-generation Open weights Also via API 12.2 B 131 K ✓ apache-2.0 191 K from 56.2 GB
402 Mistral-Small-3.2-24B-Instruct-2506 mistralai · text-generation Open weights Also via API 24.0 B — ✓ apache-2.0 188 K from 109.8 GB
403 DeepSeek-R1-0528 deepseek-ai · text-generation Open weights Also via API 684.5 B 164 K ✓ mit 165 K from 860.6 GB
404 Qwen3-Next-80B-A3B-Instruct Qwen · text-generation Open weights Also via API 81.3 B 262 K ✓ apache-2.0 154 K from 191.6 GB
405 DeepSeek-V4-Pro-0813 deepseek-ai · text-generation Open weights Also via API 1,650.5 B 1.0 M ✓ mit 151 K from 1,230.1 GB
406 MiMo-V2.5 XiaomiMiMo · text-generation Open weights Also via API 310.8 B 1.0 M ✓ mit 144 K from 394.4 GB
407 Qwen3-235B-A22B-Instruct-2507 Qwen · text-generation Open weights Also via API 235.1 B 262 K ✓ apache-2.0 139 K from 553.0 GB
408 Ministral-3-14B-Instruct-2512 mistralai · text-generation Open weights Also via API 13.9 B — ✓ apache-2.0 121 K from 37.2 GB
409 GLM-4.5 zai-org · text-generation Open weights Also via API 358.3 B 131 K ✓ mit 114 K from 842.6 GB
410 MiMo-V2.6-Pro-RL XiaomiMiMo · text-generation Open weights Also via API 1,024.2 B 1.0 M ✓ mit 96 K from 784.9 GB
411 Ministral-3-8B-Instruct-2512 mistralai · text-generation Open weights Also via API 8.9 B — ✓ apache-2.0 94 K from 24.8 GB
412 Ministral-3-3B-Instruct-2512 mistralai · text-generation Open weights Also via API 3.8 B — ✓ apache-2.0 93 K from 11.4 GB
413 MiMo-V2.6-Flash-RL XiaomiMiMo · text-generation Open weights Also via API 310.8 B 1.0 M ✓ mit 92 K from 242.6 GB
414 Hy3-preview tencent · text-generation Open weights Also via API 298.8 B 262 K other 85 K from 702.7 GB
415 GLM-4.7 zai-org · text-generation Open weights Also via API 358.3 B 203 K ✓ mit 81 K from 842.6 GB
416 granite-4.2-8b ibm-granite · text-generation Open weights Also via API 8.8 B 131 K ✓ apache-2.0 80 K from 21.2 GB
417 Mistral-Small-24B-Instruct-2501 mistralai · text-generation Open weights Also via API 23.6 B 33 K ✓ apache-2.0 74 K from 107.8 GB
418 Mistral-Small-4-119B-2603 mistralai · text-generation Open weights Also via API 119.4 B — ✓ apache-2.0 69 K from 284.4 GB
419 Hunyuan-A13B-Instruct tencent · text-generation Open weights Also via API 80.4 B 33 K other 69 K from 189.4 GB
420 Qwen3-Coder-480B-A35B-Instruct Qwen · text-generation Open weights Also via API 480.2 B 262 K ✓ apache-2.0 54 K from 1,128.9 GB
421 Kimi-K2-Thinking moonshotai · text-generation Open weights Also via API 1,026.4 B 262 K other 48 K from 808.1 GB
422 Mixtral-8x22B-Instruct-v0.1 mistralai · text-generation Open weights Also via API 140.6 B 66 K ✓ apache-2.0 46 K from 331.0 GB
423 Qwen3-Next-80B-A3B-Thinking Qwen · text-generation Open weights Also via API 81.3 B 262 K ✓ apache-2.0 38 K from 191.6 GB
424 Nemotron-3.5-Content-Safety nvidia · text-generation Open weights Also via API 4.3 B — other 35 K from 10.6 GB
425 Kimi-K2-Instruct-0905 moonshotai · text-generation Open weights Also via API 1,026.5 B 262 K other 32 K from 1,286.6 GB
426 Qwen3.8-2.4T-A95B Qwen · text-generation Open weights Also via API 2,446.2 B 262 K other 25 K from 5,749.0 GB
427 GLM-4.6 zai-org · text-generation Open weights Also via API 356.8 B 203 K ✓ mit 21 K from 839.0 GB
428 gemma-2-27b-it google · text-generation · gated Open weights Also via API 27.2 B — ⚠ gemma 20 K from 64.5 GB
429 gpt-oss-safeguard-20b openai · text-generation Open weights Also via API 21.5 B 131 K ✓ apache-2.0 19 K from 18.9 GB
430 Hy4-preview tencent · text-generation Open weights Also via API 780.0 B 1.0 M ✓ apache-2.0 18 K from 1,833.5 GB
431 LFM2.5-24B-A2B LiquidAI · text-generation Open weights Also via API 24.0 B 131 K other 18 K from 56.8 GB
432 Qwen3-235B-A22B-Thinking-2507 Qwen · text-generation Open weights Also via API 235.1 B 262 K ✓ apache-2.0 16 K from 553.0 GB
433 MiMo-V2.5-Pro XiaomiMiMo · text-generation Open weights Also via API 1,023.2 B 1.0 M ✓ mit 13 K from 1,290.7 GB
434 DeepSeek-V3.1-Terminus deepseek-ai · text-generation Open weights Also via API 684.5 B 164 K ✓ mit 13 K from 860.6 GB
435 Xing4.0-29B-A4B XingChen-AGI · text-generation Open weights Also via API 31.2 B 262 K ✓ apache-2.0 13 K from 73.9 GB
436 MiniMax-M2.1 MiniMaxAI · text-generation Open weights Also via API 228.7 B 197 K other 12 K from 288.0 GB
437 Ling-3.0-flash inclusionAI · text-generation Open weights Also via API 127.5 B 262 K ✓ mit 10 K from 300.1 GB
438 granite-4.0-h-micro ibm-granite · text-generation Open weights Also via API 3.2 B 131 K ✓ apache-2.0 9 K from 8.0 GB
439 North-Mini-Code-1.0 CohereLabs · text-generation Open weights Also via API 30.5 B 500 K ✓ apache-2.0 7 K from 72.1 GB
440 Devstral-2-123B-Instruct-2512 mistralai · text-generation Open weights Also via API 125.0 B 262 K other 5 K from 301.4 GB
441 Beam-1.0-501B-A23B reflection · text-generation Open weights Also via API 501.3 B 1.0 M ✓ apache-2.0 4 K from 1,178.6 GB
442 Cydonia-24B-v4.1 TheDrummer · text-generation Open weights Also via API 23.6 B 131 K unknown 4 K from 55.9 GB
443 Skyfall-36B-v2 TheDrummer · text-generation Open weights Also via API 36.9 B 33 K other 3 K from 87.2 GB
444 Nex-N2.5-mini nex-agi · text-generation Open weights Also via API 35.1 B — ✓ apache-2.0 3 K from 83.0 GB
445 MiniMax-Text-01 MiniMaxAI · text-generation Open weights Also via API 456.1 B 10.2 M unknown 3 K from 1,075.1 GB
446 LongCat-2.0 meituan-longcat · text-generation Open weights Also via API 1,775.6 B 262 K ✓ mit 3 K from 4,173.7 GB
447 Step-5-Preview stepfun-ai · text-generation Open weights Also via API 604.3 B — other 2 K from 806.5 GB
448 Trinity-Large-Thinking arcee-ai · text-generation Open weights Also via API 398.6 B 262 K other 2 K from 937.3 GB
449 Hermes-3-Llama-3.1-70B NousResearch · text-generation Open weights Also via API 70.6 B 131 K ⚠ llama3 2 K from 166.3 GB
450 flint RecursiveSI · text-generation Open weights Also via API 39.8 B 262 K ✓ apache-2.0 2 K from 94.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.