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 2276 · Hugging Face models 62
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 61| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| 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 · matched qwen | 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 / 1563 / 1634 / 1683597 / 1719 / 172 / 1724 / 1742 / 1754 / 1787 / 1790 / 17942 / 1840 / 1894 / 1910 / 2027 / 218 / 2217 / 2268 / 2311 / 2572 / 2638 / 29374 / 3160 / 31661 / 3255 / 3367 / 3375 / 3470 / 3592 / 438 / 4756 / 506 / 53 / 5401 / 5748 / 6578 / 703 / 904 / 910 | 2026-08-25 |
| DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1964 / 2014 / 2027 / 3304 | 2026-03-04 |
| CodeGoat24/WorldReward-qwen38-27b CodeGoat24/WorldReward-qwen38-27b · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 1457 / 75 / 83 | 2026-09-06 |
| CodeGoat24/WorldReward-qwen35-9b CodeGoat24/WorldReward-qwen35-9b · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 3 | apache-2.0 | 1134 / 157 / 172 / 3459 / 987 | 2026-08-28 |
| darrellbest/Qwen3.5-9B-Heretic darrellbest/Qwen3.5-9B-Heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 19 / 34 / 812 | 2026-09-25 |
| darrellbest/Qwen3.5-4B-Heretic darrellbest/Qwen3.5-4B-Heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 13 / 22 / 685 | 2026-09-25 |
| bottlecapai/ThinkingCap-Qwen3.8-27B bottlecapai/ThinkingCap-Qwen3.8-27B · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 8 | other | 1101 / 1449 / 151 / 1877 / 1895 / 21073 / 255 / 315 / 3347 / 609 | 2026-09-23 |
| darrellbest/Qwen3.5-2B-Heretic darrellbest/Qwen3.5-2B-Heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 18 / 28 / 390 | 2026-09-25 |
| ggml-org/Qwen3.8-27B-GGUF ggml-org/Qwen3.8-27B-GGUF · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 3 | apache-2.0 | 1075427 / 1601 / 304 / 631 | 2026-08-14 |
| darrellbest/Qwen3.8-27B-Heretic darrellbest/Qwen3.8-27B-Heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 1853 / 21 / 62 | 2026-09-24 |
| 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 · matched qwen | model 2 quantisation 2 | apache-2.0 | 1603479 / 2035504 / 438 / 4679 | 2026-09-01 |
| cyberneurova/cyberneurova-Qwen3.8-Flash-Next cyberneurova/cyberneurova-Qwen3.8-Flash-Next · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 149 / 199 / 86 | 2026-09-08 |
| GestaltLabs/Qwen3.8-27B-EXL3-11.5GB GestaltLabs/Qwen3.8-27B-EXL3-11.5GB · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 660 / 691 | 2026-09-05 |
| Blackfrost-AI/Qwen3.8-27B-ABLITERATED-BF16 Blackfrost-AI/Qwen3.8-27B-ABLITERATED-BF16 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 4 | apache-2.0 | 111 / 1373 / 1435 / 2229 / 293 / 68 | 2026-08-14 |
| ChemFM/LangMolDiode-Qwen3.5-4B-SFT ChemFM/LangMolDiode-Qwen3.5-4B-SFT · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | — | 13 / 16 / 786 | 2026-09-18 |
| darrellbest/Qwen3.5-0.8B-Heretic darrellbest/Qwen3.5-0.8B-Heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 15 / 23 / 385 | 2026-09-25 |
| andrewting/Swift-Qwen3.8-27B-Abliterated andrewting/Swift-Qwen3.8-27B-Abliterated · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | other | 13168 / 3050 / 505 / 600 | 2026-09-19 |
| akumaburn/Swift-Qwen3.8-27b-heretic akumaburn/Swift-Qwen3.8-27b-heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | other | 108 / 1125 / 1533 / 95 | 2026-09-18 |
| aacudad/AnomalyThink-Qwen3-VL-8B-KCR aacudad/AnomalyThink-Qwen3-VL-8B-KCR · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1763 / 28 / 32 / 522 | 2026-09-18 |
| agentionai/Signal-3.8-27B agentionai/Signal-3.8-27B · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 5 | apache-2.0 | 1190 / 1363 / 1793 / 401 / 503 / 509 / 705 | 2026-09-10 |
| ayoubkirouane/Sophea-Qwen3.6-v1.1 ayoubkirouane/Sophea-Qwen3.6-v1.1 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1252 / 26 / 31 / 689 | 2026-09-16 |
| dongfangshuo/Dongfangshuo-Qwen3.8-27B-NSFW dongfangshuo/Dongfangshuo-Qwen3.8-27B-NSFW · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 3 | apache-2.0 | 284 / 295 / 3572 / 4199 / 5855 | 2026-09-14 |
| ermiaazarkhalili/Qwen3.8-4B-SFT-Fable5 ermiaazarkhalili/Qwen3.8-4B-SFT-Fable5 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 44 / 47 / 821 | 2026-09-14 |
| AIcell/guava-v13b-qwen3.5-4b AIcell/guava-v13b-qwen3.5-4b · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | — | 40 / 41 / 741 | 2026-09-12 |
| apetersson/Qwen3.8-Flash-Next-GGUF apetersson/Qwen3.8-Flash-Next-GGUF · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | other | 17020 / 330 / 8953 | 2026-09-07 |
Facets
Sources
Hugging Face models primary
The model itself: its licence, its task and how many people fetch it.
model · failing1568
GGUF quantisations high
Which quantisations exist, which is what decides whether it runs on the machine somebody has.
quantisation · current8921