Models you can run yourself
A model, every quantisation somebody made of it, and what each one costs to run.
Only one source knows: GGUF quantisations 2338 · Hugging Face models 66
Covers. Every GGUF repository created since 2026-08-23, and the base model behind each one. 2,684 of those bases are named; without a Hugging Face token the run is throttled off after roughly 600 to 750 of them, so the model side of the join is partial and the scope says so on its front page. Excludes. Ollama, whose library names no Hugging Face repository to join on. Benchmarks, which have no machine-readable source.
Compared · what is held against what, and from which column of each source
| Property | Hugging Face models | GGUF quantisations |
|---|---|---|
| Licence | cardData.license | cardData.license |
Everything else the sources say is shown side by side, and not compared.
Found
1–25 of 195| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| datalab-to/chandra-ocr-2 datalab-to/chandra-ocr-2 · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | openrail | 149 / 2055581 / 2383019 / 247 | 2026-03-16 |
| DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 1603479 / 2116212 / 438 / 4679 | 2026-09-01 |
| baidu/Unlimited-OCR baidu/Unlimited-OCR · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 1442707 / 168 / 1826036 / 89 | 2026-06-19 |
| dots-studio/dots.ocr dots-studio/dots.ocr · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1013742 / 1093178 / 675 | 2025-07-30 |
| ggml-org/Qwen3.8-27B-GGUF ggml-org/Qwen3.8-27B-GGUF · Hugging Face models, GGUF quantisations | model 1 quantisation 3 | apache-2.0 | 1075427 / 1601 / 309 / 631 | 2026-08-14 |
| deepseek-ai/DeepSeek-V4-Flash-Vision-Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp · Hugging Face models, GGUF quantisations | model 2 quantisation 16 | apache-2.0 / mit / other | 1063 / 11158 / 13551 / 189004 / 212 / 2193 / 2498 / 2559 / 3355 / 36695 / 442 / 5618 / 588 / 62318 / 813 / 915320 / 925431 / 9601 | 2026-08-31 |
| deepseek-ai/DeepSeek-OCR-2 deepseek-ai/DeepSeek-OCR-2 · Hugging Face models | model 2 | apache-2.0 | 847212 | 2026-01-27 |
| deepseek-ai/DeepSeek-V4.1-Flash deepseek-ai/DeepSeek-V4.1-Flash · Hugging Face models, GGUF quantisations | model 2 quantisation 18 | apache-2.0 / mit | 0 / 1099587 / 12061 / 145 / 158 / 15890 / 1693 / 1737 / 19701 / 2157 / 25057 / 257 / 3550 / 41756 / 5384 / 640577 / 787841 / 9685 | 2026-09-10 |
| byteshape/Qwen3.8-27B-GGUF byteshape/Qwen3.8-27B-GGUF · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 318714 / 764628 / 834 | 2026-08-18 |
| empero-ai/Qwen3.8-27B-Ridge-GGUF empero-ai/Qwen3.8-27B-Ridge-GGUF · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 2895 / 408455 / 494692 | 2026-08-15 |
| dots-studio/dots.mocr dots-studio/dots.mocr · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 1499 / 151 / 277812 / 423053 | 2026-03-19 |
| autotrust/JEV-27B-VL autotrust/JEV-27B-VL · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | apache-2.0 | 267 / 308531 | 2026-09-30 |
| ATH-MaaS/OvisOCR2 ATH-MaaS/OvisOCR2 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 197760 / 236122 / 2953 | 2026-07-13 |
| BDRC/tibetan-ocr BDRC/tibetan-ocr · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 134966 / 222970 / 65 | 2026-08-17 |
| bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF bartowski/orcarouter_Qwen3.8-27B-Uncensored-GGUF · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 149031 / 152921 / 289 | 2026-08-27 |
| Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 113827 / 52 / 73931 | 2026-08-14 |
| fancyfeast/llama-joycaption-beta-one-hf-llava fancyfeast/llama-joycaption-beta-one-hf-llava · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | llama3.1 | 102709 / 112302 / 487 | 2025-05-11 |
| allenai/Molmo2-8B allenai/Molmo2-8B · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 412 / 61761 / 68863 | 2025-12-14 |
| dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8 dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 30063 / 39227 / 60561 | 2026-09-10 |
| allenai/Molmo2-4B allenai/Molmo2-4B · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | apache-2.0 | 123 / 56386 | 2025-12-14 |
| amd/Qwen3.8-27B-Quark-AWQ-MXFP4 amd/Qwen3.8-27B-Quark-AWQ-MXFP4 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 39074 / 44170 / 7019 | 2026-08-15 |
| DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU · Hugging Face models, GGUF quantisations | model 2 quantisation 51 | apache-2.0 / cc-by-4.0 / other | 0 / 1015 / 1016 / 10199 / 1088 / 12341 / 12717 / 1379 / 14563 / 1476 / 1511 / 1557 / 1559 / 15592 / 1634 / 1683597 / 1719 / 172 / 1724 / 1737 / 1754 / 1787 / 1790 / 17942 / 1840 / 1862 / 1894 / 1910 / 2027 / 2217 / 2268 / 2311 / 2572 / 2638 / 29374 / 31347 / 3160 / 3255 / 3367 / 3375 / 3470 / 3592 / 398 / 4756 / 506 / 53 / 5401 / 5748 / 6578 / 703 / 904 / 910 | 2026-08-25 |
| EldanRing/Winnow-12B EldanRing/Winnow-12B · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | apache-2.0 | 0 / 26618 | 2026-09-20 |
| allenai/olmOCR-7B-0825-FP8 allenai/olmOCR-7B-0825-FP8 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 17082 / 20456 / 235 | 2025-08-13 |
| abacusai/Smaug-Mini abacusai/Smaug-Mini · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 17917 / 18141 / 503 | 2026-09-02 |
Facets
Task 1422 of 11119 claims
Sources
Hugging Face models primary
The model itself: its licence, its task and how many people fetch it.
model · failing1654
GGUF quantisations high
Which quantisations exist, which is what decides whether it runs on the machine somebody has.
quantisation · current9465