1,222 models · 1,222 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 |
|---|---|---|---|---|---|---|
| 651 | Mistral-7B-v0.1 | 7.2 B | 33 K | ✓ apache-2.0 | 327 K | from 17.5 GB |
| 652 | Llama-3.2-3B-Instruct | 3.2 B | 131 K | ⚠ llama3.2 | 326 K | from 8.0 GB |
| 653 | gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF | — | — | ✓ apache-2.0 | 324 K | from 1.4 GB |
| 654 | GLM-5.2 | 753.3 B | 1.0 M | ✓ mit | 323 K | from 1,770.8 GB |
| 655 | Qwen3.6-14B-A3B-FableVibes-GGUF | — | — | ✓ apache-2.0 | 322 K | from 6.4 GB |
| 656 | Qwen2.5-Coder-14B-Instruct-AWQ | 14.8 B | 33 K | ✓ apache-2.0 | 322 K | from 13.7 GB |
| 657 | Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 321 K | from 3.7 GB |
| 658 | Qwen3.5-122B-A10B-NVFP4 | 64.6 B | — | ✓ apache-2.0 | 320 K | from 102.0 GB |
| 659 | Qwen-Image-2512-GGUF | — | — | ✓ apache-2.0 | 319 K | from 8.6 GB |
| 660 | distilbart-cnn-12-6 | — | 1 K | ✓ apache-2.0 | 318 K | — |
| 661 | Qwen2.5-0.5B-Instruct-GGUF | — | — | ✓ apache-2.0 | 318 K | from 1.0 GB |
| 662 | DeepSeek-V3.1 | 684.5 B | 164 K | ✓ mit | 316 K | from 860.6 GB |
| 663 | Ornith-1.5-9B-OBLITERATED | 9.7 B | — | ✓ mit | 316 K | from 6.3 GB |
| 664 | Qwen3-32B-NVFP4 | 32.0 B | 41 K | ✓ apache-2.0 | 309 K | from 28.0 GB |
| 665 | DeepSeek-R1-Distill-Qwen-7B | 7.6 B | 131 K | ✓ mit | 308 K | from 18.4 GB |
| 666 | Bonsai-27B-gguf | — | — | ✓ apache-2.0 | 305 K | from 1.2 GB |
| 667 | prokbert-mini-promoter | 20 M | 1 K | ✗ cc-by-nc-4.0 | 302 K | from 0.6 GB |
| 668 | Ornith-1.5-9B-MLX-8bit | 9.0 B | — | unknown | 302 K | from 12.3 GB |
| 669 | Ornith-1.5-9B-MLX | 9.0 B | — | unknown | 301 K | from 21.5 GB |
| 670 | DeepSeek-R1-Distill-Qwen-14B | 14.8 B | 131 K | ✓ mit | 301 K | from 35.2 GB |
| 671 | Qwen-Image | 20.4 B | — | ✓ apache-2.0 | 300 K | from 67.0 GB |
| 672 | Jan-v3.5-4B-gguf | — | — | ✓ apache-2.0 | 299 K | from 2.8 GB |
| 673 | Qwen2.5-Coder-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 297 K | from 3.8 GB |
| 674 | noobai-XL-1.1 | 2.6 B | — | other | 295 K | from 16.3 GB |
| 675 | MegaDescriptor-T-224 | — | — | ✗ cc-by-nc-4.0 | 295 K | — |
| 676 | GLM-5.3-Flash-Maya-GGUF | 321.3 B | — | ✓ mit | 294 K | from 49.9 GB |
| 677 | JiRackUltra_14b | 14.8 B | 131 K | ✓ mit | 292 K | from 9.1 GB |
| 678 | phishing-email-detection-distilbert_v2.4.1 | 70 M | 512 | ✓ apache-2.0 | 292 K | from 0.8 GB |
| 679 | voice-gender-classifier | 20 M | — | ✓ mit | 291 K | from 0.6 GB |
| 680 | Noct-Q-Uncensored-Qwen-Image-2.1 | 7.1 B | — | other | 289 K | from 17.5 GB |
| 681 | segformer-b0-finetuned-ade-512-512 | <0.1 M | — | other | 288 K | from 0.5 GB |
| 682 | opus-mt-de-en | — | 512 | ✓ apache-2.0 | 284 K | — |
| 683 | xflux_text_encoders | 4.8 B | — | ✓ apache-2.0 | 284 K | from 11.7 GB |
| 684 | convnextv2_large.fcmae_ft_in22k_in1k_384 | 200 M | — | ✗ cc-by-nc-4.0 | 284 K | from 1.4 GB |
| 685 | rtdetr_v2_r18vd | 20 M | — | ✓ apache-2.0 | 283 K | from 0.6 GB |
| 686 | phishing-distilbert-cyber207 | 67 M | 512 | unknown | 283 K | from 0.8 GB |
| 687 | koelectra-small-v3-nsmc | 10 M | 512 | ✓ mit | 283 K | from 0.6 GB |
| 688 | Qwen2.5-7B-Instruct-GPTQ-Int4 | 7.6 B | 33 K | ✓ apache-2.0 | 282 K | from 7.8 GB |
| 689 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 282 K | from 3.1 GB |
| 690 | Olmo-3-7B-Instruct | 7.3 B | 66 K | ✓ apache-2.0 | 279 K | from 17.7 GB |
| 691 | Qwen3-0.6B-GGUF | 600 M | 41 K | ✓ apache-2.0 | 279 K | from 1.3 GB |
| 692 | zeta-2.1-autoround-W4A16 | 2.2 B | 33 K | unknown | 275 K | from 7.6 GB |
| 693 | convnext_tiny.fb_in22k_ft_in1k | 29 M | — | ✓ apache-2.0 | 275 K | from 0.6 GB |
| 694 | vit_tiny_r_s16_p8_224.augreg_in21k | 10 M | — | ✓ apache-2.0 | 274 K | from 0.5 GB |
| 695 | Qwen-AgentWorld-35B-A3B-GGUF | — | — | ✓ apache-2.0 | 273 K | from 13.1 GB |
| 696 | fullstop-punctuation-multilang-large | 560 M | 512 | ✓ mit | 273 K | from 3.0 GB |
| 697 | ner-english | — | — | unknown | 272 K | — |
| 698 | CodonTransformer | 90 M | 4 K | ✓ apache-2.0 | 270 K | from 0.9 GB |
| 699 | llm-jp-4-33b-thinking-gguf | 33.0 B | — | ✓ apache-2.0 | 269 K | from 27.6 GB |
| 700 | Qwopus3.6-27B-Fusion-GGUF | — | — | other | 268 K | from 15.4 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.