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 85| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| DreamFast/gemma-3-12b-it-heretic DreamFast/gemma-3-12b-it-heretic · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | gemma | 10962 / 13221 / 557 | 2026-01-11 |
| mradermacher/Boulesis-26B-A4B-i1-GGUF SubMaroon/Boulesis-26B-A4B · GGUF quantisations | quantisation 5 | gemma | 15698 | 2026-09-05 |
| mradermacher/Boulesis-v2.1-26B-A4B-i1-GGUF SubMaroon/Boulesis-v2.1-26B-A4B · GGUF quantisations | quantisation 2 | gemma | 12192 | 2026-09-14 |
| DomainLLM/gemma-3-12b-it-law-fine-tuned DomainLLM/gemma-3-12b-it-law-fine-tuned · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | gemma | 136 / 83 / 92 | 2026-03-25 |
| mradermacher/Boulesis-v2-26B-A4B-i1-GGUF SubMaroon-exp/Boulesis-v2-26B-A4B · GGUF quantisations | quantisation 2 | gemma | 1451 | 2026-09-13 |
| distil-labs/Distil-NPC-gemma-3-270m distil-labs/Distil-NPC-gemma-3-270m · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | gemma | 122 / 22 / 24 | 2025-10-23 |
| 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 |
| bigmoveintelligent/chatter-12b-v1 bigmoveintelligent/chatter-12b-v1 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | gemma | 11 / 13 / 391 | 2026-09-22 |
| mradermacher/Boulesis-v2.1-26B-A4B-HeadTune-i1-GGUF SubMaroon/Boulesis-v2.1-26B-A4B-HeadTune · GGUF quantisations | quantisation 1 | gemma | 5933 | 2026-09-20 |
| dams2005/gemma-3-4b-it-triplet-extractor dams2005/gemma-3-4b-it-triplet-extractor · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | gemma | 11 / 69 | 2026-06-01 |
| mradermacher/gemma-4-A4B-98e-v5-coder-it-i1-GGUF ManniX-ITA/gemma-4-A4B-98e-v5-coder-it · GGUF quantisations | quantisation 2 | gemma | 5486 | 2026-09-25 |
| jialinyyzz/humanizer-gemma-4-e4b google/gemma-4-E4B · GGUF quantisations | quantisation 5 | apache-2.0 | 143 | 2026-09-04 |
| bigmoveintelligent/chatter-4b-v1 bigmoveintelligent/chatter-4b-v1 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | gemma | 373 / 7 / 9 | 2026-09-20 |
| mradermacher/amethyst-1-mini-i1-GGUF VertexAGI/amethyst-1-mini · GGUF quantisations | quantisation 2 | gemma | 1264 | 2026-08-31 |
| mradermacher/gemma-4-E2B-home-assistant-i1-GGUF mewse/gemma-4-E2B-home-assistant · GGUF quantisations | quantisation 2 | gemma | 1214 | 2026-09-15 |
| BricksDisplay/jevling-2b-v0.1 BricksDisplay/jevling-2b-v0.1 · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | gemma | 2 / 59 | 2026-09-28 |
| BricksDisplay/jevling-e2b-v0.1 BricksDisplay/jevling-e2b-v0.1 · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | gemma | 2 / 59 | 2026-09-28 |
| mradermacher/sommerfugl-31b-v1-i1-GGUF oolabs/sommerfugl-31b-v1 · GGUF quantisations | quantisation 2 | gemma | 3406 | 2026-10-01 |
| mradermacher/jevify-gemma4-e4b-GGUF kushalpatil/jevify-gemma4-e4b · GGUF quantisations | quantisation 1 | gemma | 3284 | 2026-09-20 |
| 26B-Suite/Dark-Goetia-26B-A4B-v2 26B-Suite/Dark-Goetia-26B-A4B-v2 · Hugging Face models | model 2 | gemma | 0 | 2026-08-16 |
| mradermacher/SAEVerbalizer-27B-i1-GGUF THU-KEG/SAEVerbalizer-27B · GGUF quantisations | quantisation 2 | gemma | 2972 | 2026-09-02 |
| Aratako/Irodori-TTS-v4-Large Aratako/Irodori-TTS-v4-Large · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | gemma | 0 / 65 | 2026-09-27 |
| mradermacher/gemma-3-12b-it-antislop-de-i1-GGUF PhilflowIO/gemma-3-12b-it-antislop-de · GGUF quantisations | quantisation 2 | gemma | 2779 | 2026-09-06 |
| projectj/Instinct-Python-Coder-Gemma4-12B-Qwen3.8-27B unsloth/gemma-4-12b-it · GGUF quantisations | quantisation 1 | gemma | 2118 | 2026-09-12 |
Facets
Licence 8607 of 11119 claims
gemma172
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