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.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 451 | Higgs-Audio-v3-Studio | — | — | other | 560 K | from 5.0 GB |
| 452 | animagine-xl-4.0 | 2.6 B | — | ⚠ openrail++ | 560 K | from 23.8 GB |
| 453 | nomic-embed-text-v1.5-GGUF | 140 M | 2 K | ✓ apache-2.0 | 557 K | from 0.6 GB |
| 454 | Qwen2.5-Coder-32B-Instruct | 32.8 B | 33 K | ✓ apache-2.0 | 556 K | from 77.5 GB |
| 455 | OTel-2.0-Decision-26B-A4B-4bit | 25.8 B | — | ✓ apache-2.0 | 555 K | from 23.3 GB |
| 456 | FRIDA | 823 M | — | ✓ mit | 553 K | from 4.2 GB |
| 457 | Qwen3.8-4B-Distill-GGUF | — | — | ✓ apache-2.0 | 552 K | from 3.6 GB |
| 458 | wavlm-base-plus | — | — | unknown | 550 K | — |
| 459 | fasttext-language-identification | — | — | ✗ cc-by-nc-4.0 | 546 K | — |
| 460 | Llama-3.2-1B | 1.2 B | — | ⚠ llama3.2 | 545 K | from 3.4 GB |
| 461 | Qwen3.8-Flash-Next-GGUF | 180.0 B | — | other | 545 K | from 28.5 GB |
| 462 | embeddinggemma-300m-ONNX | 300 M | 2 K | ⚠ gemma | 542 K | from 1.2 GB |
| 463 | MiniCPM5-2B-MLX | 2.5 B | 131 K | ✓ apache-2.0 | 541 K | from 2.4 GB |
| 464 | open-vakgyata | 60 M | — | ✗ cc-by-nc-4.0 | 540 K | from 0.8 GB |
| 465 | NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | 67.2 B | 262 K | other | 540 K | from 98.9 GB |
| 466 | gpt-oss-20b-GGUF | — | 131 K | ✓ apache-2.0 | 539 K | from 13.1 GB |
| 467 | Underdog-Saluki-27B-1.0 | 27.0 B | — | ✓ apache-2.0 | 535 K | from 5.2 GB |
| 468 | EXAONE-3.5-7.8B-Instruct-AWQ | 7.8 B | 33 K | other | 530 K | from 7.5 GB |
| 469 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 529 K | from 3.2 GB |
| 470 | wav2vec2-large-xlsr-kazakh | 320 M | — | ✓ apache-2.0 | 526 K | from 1.9 GB |
| 471 | macbert4csc-base-chinese | 100 M | 512 | ✓ apache-2.0 | 526 K | from 1.0 GB |
| 472 | FLUX.1-schnell | 11.9 B | — | ✓ apache-2.0 | 523 K | from 65.9 GB |
| 473 | Ornith-1.5-35B-A3B-FP8 | 36.0 B | — | ✓ mit | 523 K | from 49.2 GB |
| 474 | Qwen3.8-9B-Distill-GGUF | — | — | ✓ apache-2.0 | 523 K | from 6.9 GB |
| 475 | Qwen3.8-27B-OBLITERATED | 27.8 B | — | ✓ apache-2.0 | 520 K | from 5.7 GB |
| 476 | Qwen3.8-27B-NVFP4 | 27.0 B | — | ✓ apache-2.0 | 516 K | from 28.7 GB |
| 477 | Qwen3-Coder-Next | 79.7 B | 262 K | ✓ apache-2.0 | 516 K | from 187.7 GB |
| 478 | Pruna-Q-Image-2.1 | 7.1 B | — | other | 515 K | from 2.3 GB |
| 479 | jina-embeddings-v5-text-nano | 210 M | 8 K | ✗ cc-by-nc-4.0 | 515 K | from 1.1 GB |
| 480 | whisper-large-v3-turbo-gguf | 810 M | — | ✓ mit | 515 K | from 1.2 GB |
| 481 | Pruna-Qage-2.1 | 7.1 B | — | other | 514 K | from 2.3 GB |
| 482 | Pruna-Qwen-Image-2.1 | 7.1 B | — | other | 513 K | from 2.3 GB |
| 483 | wav2vec2-large-xlsr-53-estonian | — | — | ✓ apache-2.0 | 513 K | — |
| 484 | POCKET-35B-GGUF | 35.0 B | — | ✓ apache-2.0 | 511 K | from 14.8 GB |
| 485 | Ternary-Bonsai-27B-gguf | — | — | ✓ apache-2.0 | 506 K | from 1.2 GB |
| 486 | Qwen-Image-2.1-viggle-turbo | 7.1 B | — | other | 504 K | from 6.3 GB |
| 487 | Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 | 7.6 B | 33 K | ✓ apache-2.0 | 504 K | from 7.8 GB |
| 488 | msmarco-bert-base-dot-v5 | 110 M | 512 | unknown | 503 K | from 1.0 GB |
| 489 | Qwen3-4B-GGUF | — | 41 K | ✓ apache-2.0 | 503 K | from 2.3 GB |
| 490 | Meta-Llama-3.1-8B-Instruct-GGUF | — | — | ⚠ llama3.1 | 501 K | from 3.7 GB |
| 491 | Llama-3.2-3B-Instruct-FP8-dynamic | 3.6 B | 131 K | ⚠ llama3.2 | 498 K | from 5.9 GB |
| 492 | MedCPT-Cross-Encoder | — | 512 | other | 498 K | — |
| 493 | emotion-english-distilroberta-base | — | 512 | unknown | 497 K | — |
| 494 | snowflake-arctic-embed-s | 30 M | 512 | ✓ apache-2.0 | 496 K | from 0.7 GB |
| 495 | hubert-base-ls960 | — | — | ✓ apache-2.0 | 496 K | — |
| 496 | Qwen-Image-2.1-Turbo-Uncensored-GGUF | 8.8 B | — | ✓ apache-2.0 | 493 K | from 5.5 GB |
| 497 | Qwen2.5-32B-Instruct-GPTQ-Int4 | 32.8 B | 33 K | ✓ apache-2.0 | 493 K | from 26.7 GB |
| 498 | stable-diffusion-v1-4 | 860 M | — | ⚠ creativeml-openrail-m | 492 K | from 13.5 GB |
| 499 | orcarouter_GLM-5.3-Flash-Uncensored-GGUF | 321.3 B | — | ✓ mit | 492 K | from 49.9 GB |
| 500 | Olmo-3-7B-Think | 7.3 B | 66 K | ✓ apache-2.0 | 488 K | from 17.7 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.