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
1–19 of 19| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| mradermacher/Kanimus-26B-A4B-FFT-heretic-i1-GGUF SubMaroon-exp/Kanimus-26B-A4B-FFT-heretic · GGUF quantisations | quantisation 2 | gemma | 2241 | 2026-08-28 |
| 26B-Suite/Dark-Goetia-26B-A4B-v4 26B-Suite/Dark-Goetia-26B-A4B-v4 · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | gemma | 0 / 1537 / 8179 | 2026-08-31 |
| mradermacher/amethyst-1-mini-i1-GGUF VertexAGI/amethyst-1-mini · GGUF quantisations | quantisation 2 | gemma | 1264 | 2026-08-31 |
| mradermacher/SAEVerbalizer-27B-i1-GGUF THU-KEG/SAEVerbalizer-27B · GGUF quantisations | quantisation 2 | gemma | 2972 | 2026-09-02 |
| marafx2007/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive google/gemma-4-e4b-it · GGUF quantisations | quantisation 33 | apache-2.0 | 0 | 2026-08-27 |
| DK4AAD/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced google/gemma-4-12B-it · GGUF quantisations | quantisation 30 | apache-2.0 | 1072 | 2026-08-27 |
| voidsip/gemma-4-26B-A4B-it-abliterated-Q4_0-GGUF huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-GGUF · GGUF quantisations | quantisation 1 | gemma | 1009 | 2026-09-01 |
| voidsip/gemma-4-26B-A4B-it-abliterated-Q4_0-GGUF google/gemma-4-26B-A4B-it · GGUF quantisations | quantisation 16 | apache-2.0 | 0 | 2026-09-01 |
| iromu/Gemma3-1B-tools-GGUF google/gemma-3-1b-it · GGUF quantisations | quantisation 13 | apache-2.0 | 106 | 2026-08-28 |
| VertexAGI/amethyst-1.5-mini google/gemma-3-4b-it · GGUF quantisations | quantisation 6 | apache-2.0 | 210 | 2026-08-27 |
| mehmettozlu/Turkish-Gemma-2-9B-IT-GGUF google/gemma-2-9b-it · GGUF quantisations | quantisation 2 | gemma | 365 | 2026-08-27 |
| pearsonkyle/gemma4-e4b-coder-gguf pearsonkyle/gemma4-e4b-coder · GGUF quantisations | quantisation 1 | gemma | 292 | 2026-09-02 |
| dknguyen2304/MiLMMT-46-4B-vien-GGUF xiaomi-research/MiLMMT-46-4B-v1.0 · GGUF quantisations | quantisation 1 | gemma | 135 | 2026-09-02 |
| worldboss/lauki-qna-gemma3-270m-it-gguf unsloth/gemma-3-270m-it · GGUF quantisations | quantisation 1 | gemma | 113 | 2026-08-31 |
| shimbaaa/shifu-smart-gguf google/functiongemma-270m-it · GGUF quantisations | quantisation 5 | gemma | 0 | 2026-08-28 |
| johnhalloran/goramen-blog-gemma-4-sft-gguf johnhalloran/goramen-blog-gemma-4-sft · GGUF quantisations | quantisation 1 | gemma | 106 | 2026-08-31 |
| SubMaroon/Dark-Goetia-26B-A4B-LoRA-v4-GGUF Naphula/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA · GGUF quantisations | quantisation 1 | gemma | 102 | 2026-08-26 |
| zw89/gemma-2-2b-it-Q4_K_M-GGUF google/gemma-2-2b-it · GGUF quantisations | quantisation 4 | gemma | 139 | 2026-08-28 |
| manfye/PetInst-LLM-1B-GGUF manfye/PetInst-LLM-1B-MLX · GGUF quantisations | quantisation 1 | gemma | 0 | 2026-08-27 |
Facets
Licence 8092 of 10489 claims
gemma145
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