1,213 models · 1,213 open weights · 210 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 | On RTX 4090 · 24 GB |
|---|---|---|---|---|---|---|
| 451 | Meta-Llama-3.1-8B-Instruct-AWQ-INT4 | 8.0 B | 131 K | ⚠ llama3.1 | 321 K | 8.0 GB |
| 452 | Phi-3-mini-4k-instruct | 3.8 B | 4 K | ✓ mit | 321 K | 9.5 GB |
| 453 | Ornith-1.0-9B-AWQ-INT4 | 9.4 B | — | ✓ mit | 317 K | 11.8 GB |
| 454 | Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 315 K | 4.0 GB |
| 455 | regnety_032.ra_in1k | 20 M | — | ✓ apache-2.0 | 314 K | 0.6 GB |
| 456 | opus-mt-fr-en | 80 M | 512 | ✓ apache-2.0 | 312 K | 0.8 GB |
| 457 | macbert4csc-base-chinese | 100 M | 512 | ✓ apache-2.0 | 312 K | 1.0 GB |
| 458 | phishing-email-detection-distilbert_v2.4.1 | 70 M | 512 | ✓ apache-2.0 | 311 K | 0.8 GB |
| 459 | flint-GGUF | 39.8 B | 262 K | ✓ apache-2.0 | 308 K | 19.0 GB |
| 460 | mms-lid-1024 | 967 M | — | ✗ cc-by-nc-4.0 | 308 K | 4.9 GB |
| 461 | gpt-oss-120b-GGUF | 120.0 B | 131 K | ✓ apache-2.0 | 306 K | 19.4 GB |
| 462 | Qwen3-1.7B | 2.0 B | 41 K | ✓ apache-2.0 | 306 K | 5.3 GB |
| 463 | prokbert-mini-promoter | 20 M | 1 K | ✗ cc-by-nc-4.0 | 302 K | 0.6 GB |
| 464 | vit_small_patch16_224.augreg_in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 302 K | 0.6 GB |
| 465 | pythia-14m | 10 M | 2 K | ✓ apache-2.0 | 299 K | 0.5 GB |
| 466 | GLM-4.7-Flash-GGUF | — | — | ✓ mit | 296 K | 13.0 GB |
| 467 | nllb-200-3.3B | 3.3 B | 1 K | ✗ cc-by-nc-4.0 | 296 K | 8.3 GB |
| 468 | Apertus-8B-Instruct-2509 | 8.1 B | 66 K | ✓ apache-2.0 | 295 K | 19.4 GB |
| 469 | JiRackUltra_14b | 14.8 B | 131 K | ✓ mit | 292 K | 9.1 GB |
| 470 | voice-gender-classifier | 20 M | — | ✓ mit | 291 K | 0.6 GB |
| 471 | Qwen2.5-3B-Instruct-GGUF | — | — | other | 291 K | 2.0 GB |
| 472 | Qwen2.5-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 288 K | 3.6 GB |
| 473 | xflux_text_encoders | 4.8 B | — | ✓ apache-2.0 | 288 K | 11.7 GB |
| 474 | resnet50.fb_swsl_ig1b_ft_in1k | 26 M | — | ✗ cc-by-nc-4.0 | 288 K | 0.6 GB |
| 475 | animagine-xl-3.1 | 2.6 B | — | ⚠ openrail++ | 286 K | 16.1 GB |
| 476 | segformer-b0-finetuned-ade-512-512 | <0.1 M | — | other | 286 K | 0.5 GB |
| 477 | gpt2-mini | 39 M | — | ✓ mit | 285 K | 0.7 GB |
| 478 | controlnet-openpose-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 285 K | 6.2 GB |
| 479 | LFM3-1.7B-GGUF | 1.7 B | — | other | 283 K | 1.9 GB |
| 480 | koelectra-small-v3-nsmc | 10 M | 512 | ✓ mit | 283 K | 0.6 GB |
| 481 | OpenMed-NER-PharmaDetect-SuperClinical-434M | 430 M | 512 | ✓ apache-2.0 | 279 K | 1.5 GB |
| 482 | vit_base_patch8_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 279 K | 0.9 GB |
| 483 | Qwen3-14B-FP8 | 14.8 B | 41 K | ✓ apache-2.0 | 277 K | 20.7 GB |
| 484 | Qwen2-7B-Instruct | 7.6 B | 33 K | ✓ apache-2.0 | 276 K | 18.4 GB |
| 485 | vit_tiny_patch16_224.augreg_in21k_ft_in1k | 10 M | — | ✓ apache-2.0 | 276 K | 0.5 GB |
| 486 | convnext_tiny.fb_in22k_ft_in1k | 29 M | — | ✓ apache-2.0 | 275 K | 0.6 GB |
| 487 | LFM2.5-230M-Base | 230 M | 128 K | other | 275 K | 1.0 GB |
| 488 | IP-Adapter-FaceID | — | — | unknown | 274 K | 1.5 GB |
| 489 | Ternary-Bonsai-27B-gguf | — | — | ✓ apache-2.0 | 274 K | 1.2 GB |
| 490 | vit_tiny_r_s16_p8_224.augreg_in21k | 10 M | — | ✓ apache-2.0 | 274 K | 0.5 GB |
| 491 | LFM2.5-24B-A2B-GGUF | 24.0 B | 131 K | other | 273 K | 19.0 GB |
| 492 | edgenext_small.usi_in1k | 10 M | — | ✓ mit | 271 K | 0.5 GB |
| 493 | table-transformer-detection | 30 M | 1 K | ✓ mit | 270 K | 0.6 GB |
| 494 | CodonTransformer | 90 M | 4 K | ✓ apache-2.0 | 270 K | 0.9 GB |
| 495 | Llama-3.2-3B | 3.2 B | — | ⚠ llama3.2 | 269 K | 8.0 GB |
| 496 | Noct-Q-Uncensored-Qwen-Image-2.1 | 7.1 B | — | other | 269 K | 17.5 GB |
| 497 | SmolLM2-1.7B-Instruct | 1.7 B | 8 K | ✓ apache-2.0 | 267 K | 4.5 GB |
| 498 | taardis-27b-full-ternary | 27.0 B | — | ✓ apache-2.0 | 267 K | 12.4 GB |
| 499 | Kimi-K3-DSpark | 2.3 B | 1.0 M | unknown | 266 K | 5.8 GB |
| 500 | gliner2.5-multi-v1 | 287 M | — | ✓ apache-2.0 | 266 K | 1.8 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.