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 2229 · Hugging Face models 63
Behind: zetlyn/models-hf has not completed an update.
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
76–100 of 2,276| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| 3MPER0RR/gemma-4-31b-it-3MPER0RR-abliterated 3MPER0RR/gemma-4-31b-it-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 107 / 11163 / 134 / 2474 | 2026-09-01 |
| DrMoriarty0/Qwen3.5-35B-A3B-GGUF Qwen/Qwen3.5-35B-A3B · GGUF quantisations | quantisation 9 | apache-2.0 | 11132 | 2026-08-30 |
| OS-Software/gemma-4-26B-A4B-it-qat-q4_0-heretic-japanese-pruned-GGUF google/gemma-4-26B-A4B-it · GGUF quantisations | quantisation 17 | apache-2.0 | 0 | 2026-09-01 |
| mradermacher/Gemma-4-31B-Abliterated-Uncensored-i1-GGUF Madras1/Gemma-4-31B-Abliterated-Uncensored · GGUF quantisations | quantisation 2 | apache-2.0 | 10223 | 2026-09-06 |
| jan1k/Qwen3.8-27B-Uncensored-Genesis-V1-NVFP4-GGUF LuffyTheFox/Qwen3.8-27B-Uncensored-Genesis-V1-MTP-GGUF · GGUF quantisations | quantisation 2 | apache-2.0 | 954 | 2026-09-09 |
| Jab1718/qwen3.8-flash-coder-26gb-gguf Jab1718/qwen3.8-flash-coder-85gb-bf16 · GGUF quantisations | quantisation 3 | apache-2.0 | 6002 | 2026-09-07 |
| Cyclone-Labs/Eclipsed-Phoenix-26B-A4B Cyclone-Labs/Eclipsed-Phoenix-26B-A4B · Hugging Face models, GGUF quantisations | model 2 quantisation 3 | apache-2.0 | 153 / 171 / 2969 / 7748 / 9785 | 2026-09-05 |
| mradermacher/Gemma-4-31B-Fable-5-Agent-Distill-i1-GGUF TeichAI/Gemma-4-31B-Fable-5-Agent-Distill · GGUF quantisations | quantisation 2 | apache-2.0 | 1464 | 2026-09-25 |
| 3MPER0RR/gemma-4-12b-it-3MPER0RR-abliterated 3MPER0RR/gemma-4-12b-it-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 259 / 271 / 7216 / 9495 | 2026-09-01 |
| 0xSojalSec/Tencent-Hy-30B-A3B-uncensored-heretic 0xSojalSec/Tencent-Hy-30B-A3B-uncensored-heretic · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 133 / 9384 / 95 / 982 | 2026-08-30 |
| prithivMLmods/OxCoder-9B-GGUF OrionLLM/OxCoder-9B · GGUF quantisations | quantisation 8 | apache-2.0 | 0 | 2026-09-08 |
| FINAL-Bench/Darwin-27B-RSI FINAL-Bench/Darwin-27B-RSI · Hugging Face models, GGUF quantisations | model 1 quantisation 4 | apache-2.0 | 1035 / 3023 / 419 / 905 / 9294 | 2026-09-27 |
| fwizzer1/Fwizzer-R1-3B-RU-v2 unsloth/Ministral-3-3B-Instruct-2512-bnb-4bit · GGUF quantisations | quantisation 3 | apache-2.0 | 2493 | 2026-09-05 |
| Atomic-Germ/Qwen3.8-9B-Distill-GGUF empero-ai/Qwen3.8-9B · GGUF quantisations | quantisation 1 | apache-2.0 | 9278 | 2026-09-12 |
| gashapon/Qwen3.8-27B-ROCmFPX · GGUF quantisations | quantisation 1 | apache-2.0 | 9136 | 2026-09-01 |
| Agnes-AI/Agnes-3.0-Flash Agnes-AI/Agnes-3.0-Flash · Hugging Face models, GGUF quantisations | model 2 quantisation 6 | apache-2.0 | 0 / 115 / 1627 / 202 / 2174 / 2338 / 5729 / 9123 | 2026-09-11 |
| mradermacher/TripleTrouble-i1-GGUF OliviaRossi/TripleTrouble · GGUF quantisations | quantisation 2 | apache-2.0 | 1260 | 2026-09-11 |
| davidxifeng/zipvoice-gguf k2-fsa/ZipVoice · GGUF quantisations | quantisation 1 | apache-2.0 | 8887 | 2026-09-18 |
| Blazed-Forge/Gemma-4-Sphinsikus-Chronist-V2-31B Blazed-Forge/Gemma-4-Sphinsikus-Chronist-V2-31B · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 2013 / 44 / 59 / 8621 | 2026-08-30 |
| Chonlyshoes/SMOL_BY_CHONLYSHOES.gguf · GGUF quantisations | quantisation 1 | apache-2.0 | 8619 | 2026-09-07 |
| rarad/test-gguf · GGUF quantisations | quantisation 1 | apache-2.0 | 8597 | 2026-09-08 |
| mradermacher/Qwen3.8-27B-OBLITERATED-Mythos-Class-Agentic-GGUF medismera/Qwen3.8-27B-OBLITERATED-Mythos-Class-Agentic · GGUF quantisations | quantisation 2 | apache-2.0 | 6025 | 2026-09-07 |
| mradermacher/GraphForge-Qwen3.6-35B-A3B-SFT-i1-GGUF randomsubmit/GraphForge-Qwen3.6-35B-A3B-SFT · GGUF quantisations | quantisation 2 | apache-2.0 | 630 | 2026-09-26 |
| tchbcb/samai-8b-M8 Qwen/Qwen3.5-9B · GGUF quantisations | quantisation 73 | apache-2.0 | 0 | 2026-08-28 |
| VoidWalkercero/Qwen3-0.6B-Particle-SousVide-R128-Perfect Qwen/Qwen3-0.6B · GGUF quantisations | quantisation 48 | apache-2.0 | 100 | 2026-08-26 |
Facets
Licence 8160 of 10579 claims
apache-2.04532
Sources
Hugging Face models primary
The model itself: its licence, its task and how many people fetch it.
model · partial1568
GGUF quantisations high
Which quantisations exist, which is what decides whether it runs on the machine somebody has.
quantisation · current9011