1,226 models · 1,226 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.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 351 | e5-large-v2 | 340 M | 512 | ✓ mit | 849 K | from 2.0 GB |
| 352 | dreamshaper-7 | 860 M | — | ⚠ creativeml-openrail-m | 846 K | from 9.7 GB |
| 353 | ko-sroberta-multitask | 110 M | 512 | unknown | 844 K | from 1.0 GB |
| 354 | Qwen2.5-3B-Instruct-AWQ | 3.4 B | 33 K | other | 841 K | from 4.0 GB |
| 355 | Hy3 | 298.8 B | 262 K | ✓ apache-2.0 | 837 K | from 702.7 GB |
| 356 | Qwen3-0.6B | 752 M | 41 K | ✓ apache-2.0 | 836 K | from 2.3 GB |
| 357 | Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced | 12.0 B | — | ⚠ gemma | 832 K | from 2.6 GB |
| 358 | gemma-4-26B-A4B-it-AWQ-4bit | 25.8 B | — | ✓ apache-2.0 | 830 K | from 23.3 GB |
| 359 | rorshark-vit-base | 90 M | — | ✓ apache-2.0 | 829 K | from 0.9 GB |
| 360 | Qwen3.6-27B-NVFP4 | 18.2 B | — | ✓ apache-2.0 | 827 K | from 27.3 GB |
| 361 | DeepSeek-V4-Flash | 158.1 B | 1.0 M | ✓ mit | 809 K | from 199.8 GB |
| 362 | gpt2-large | 810 M | — | ✓ mit | 801 K | from 4.2 GB |
| 363 | Qwen2.5-14B-Instruct | 14.8 B | 33 K | ✓ apache-2.0 | 799 K | from 35.2 GB |
| 364 | specter2_base | — | 512 | ✓ apache-2.0 | 796 K | — |
| 365 | Ornith-1.0-9B | <0.1 M | — | ✓ mit | 792 K | from 21.2 GB |
| 366 | RealVisXL_V5.0 | 2.6 B | — | ⚠ openrail++ | 781 K | from 46.7 GB |
| 367 | Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit | 30.0 B | 262 K | ✓ apache-2.0 | 780 K | from 24.9 GB |
| 368 | JEV-35B | 36.0 B | — | ✓ apache-2.0 | 776 K | from 85.0 GB |
| 369 | repeat | — | — | unknown | 765 K | from 0.5 GB |
| 370 | Ornith-1.5-9B-NVFP4 | 6.7 B | — | ✓ mit | 763 K | from 11.2 GB |
| 371 | whisper-tiny.en | — | — | ✓ apache-2.0 | 759 K | — |
| 372 | wav2vec2-large-xlsr-mvc-swahili | 320 M | — | ✓ apache-2.0 | 757 K | from 1.9 GB |
| 373 | Qwen3-VL-Embedding-2B | 2.1 B | — | ✓ apache-2.0 | 757 K | from 5.5 GB |
| 374 | all_miniLM_L6_v2_with_attentions | — | 512 | ✓ apache-2.0 | 753 K | — |
| 375 | resnet34.a1_in1k | 20 M | — | ✓ apache-2.0 | 752 K | from 0.6 GB |
| 376 | BiRefNet | 220 M | — | ✓ mit | 751 K | from 1.0 GB |
| 377 | faster-whisper-base.en | — | — | ✓ mit | 743 K | — |
| 378 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 31.6 B | 262 K | other | 743 K | from 77.6 GB |
| 379 | USER2-base | 149 M | 8 K | ✓ apache-2.0 | 740 K | from 1.2 GB |
| 380 | bert-large-cased-finetuned-conll03-english | 330 M | 512 | unknown | 737 K | from 2.0 GB |
| 381 | convnext_tiny.in12k_ft_in1k | 30 M | — | ✓ apache-2.0 | 735 K | from 0.6 GB |
| 382 | wavlm-large | — | — | unknown | 735 K | — |
| 383 | DeepSeek-V3-0324 | 684.5 B | 164 K | ✓ mit | 734 K | from 860.6 GB |
| 384 | sd-turbo | 870 M | — | unknown | 732 K | from 14.9 GB |
| 385 | resnet-18 | 12 M | — | ✓ apache-2.0 | 728 K | from 0.6 GB |
| 386 | wav2vec2-large-xls-r-300m-welsh | 300 M | — | ✓ apache-2.0 | 727 K | from 1.2 GB |
| 387 | whisper-tiny | 40 M | — | ✓ apache-2.0 | 727 K | from 0.7 GB |
| 388 | Qwen2.5-Math-PRM-7B | 7.6 B | 4 K | other | 719 K | from 18.4 GB |
| 389 | SmolLM3-3B | 3.1 B | 66 K | ✓ apache-2.0 | 719 K | from 7.7 GB |
| 390 | Qwen3-8B-Base | 8.2 B | 33 K | ✓ apache-2.0 | 718 K | from 19.7 GB |
| 391 | Qwen3.8-27B-NVFP4-MTP-GGUF | 27.0 B | — | ✓ apache-2.0 | 714 K | from 41.0 GB |
| 392 | ms-marco-MiniLM-L-6-v2 | — | 512 | unknown | 710 K | — |
| 393 | resnet50.ram_in1k | 30 M | — | ✓ apache-2.0 | 709 K | from 0.6 GB |
| 394 | Qwen3-32B-AWQ | 32.8 B | 41 K | ✓ apache-2.0 | 707 K | from 26.7 GB |
| 395 | finbert-tone | — | 512 | unknown | 702 K | — |
| 396 | wide_resnet50_2.racm_in1k | 70 M | — | ✓ apache-2.0 | 698 K | from 0.8 GB |
| 397 | Qwen2.5-Coder-7B-Instruct-AWQ | 7.6 B | 33 K | ✓ apache-2.0 | 697 K | from 7.8 GB |
| 398 | yolos-small | 30 M | — | ✓ apache-2.0 | 697 K | from 0.6 GB |
| 399 | parakeet-tdt-0.6b-v3-gguf | 600 M | — | ✓ cc-by-4.0 | 692 K | from 1.1 GB |
| 400 | llama-3.3-70b-instruct-awq | 70.6 B | 131 K | ⚠ llama3.3 | 691 K | from 54.8 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.