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.
Things
25 things, from 2,457 claims| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| allenai/Olmo-3-7B-Instruct allenai/Olmo-3-7B-Instruct · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 444964 / 484684 / 741 / 97 | 2025-11-19 |
| cruizba/ISTA-DASLab-Qwen3.8-27B-GSQ-RCO-GGUF-Unsloth-MTP ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF · GGUF quantisations | quantisation 5 | apache-2.0 | 13734 | 2026-08-31 |
| cruizba/ISTA-DASLab-Qwen3.8-27B-GSQ-RCO-GGUF-Unsloth-MTP unsloth/Qwen3.8-27B-GGUF · GGUF quantisations | quantisation 13 | apache-2.0 | 0 | 2026-08-30 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B deepseek-ai/DeepSeek-R1-Distill-Qwen-32B · Hugging Face models, GGUF quantisations | model 1 quantisation 2 | mit | 0 / 449261 / 64 | 2025-01-20 |
| BreezeBlue/Breeze-TTS-2 BreezeBlue/Breeze-TTS-2 · Hugging Face models, GGUF quantisations | model 2 quantisation 4 | other | 12926 / 13392 / 13570 / 1927 / 558 / 946 | 2026-08-25 |
| ampixa/sanoTTS ampixa/sanoTTS · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | gpl-3.0 | 344371 / 430717 / 683 | 2026-07-13 |
| SpeakoFlow/speakoflow-mini Qwen/Qwen3.5-0.8B · GGUF quantisations | quantisation 42 | apache-2.0 | 0 | 2026-08-28 |
| dots-studio/dots.mocr dots-studio/dots.mocr · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 120 / 1499 / 384783 / 423053 | 2026-03-19 |
| black-forest-labs/FLUX.2-klein-4B black-forest-labs/FLUX.2-klein-4B · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | apache-2.0 | 400725 / 405526 / 69 | 2026-01-14 |
| LuffyTheFox/Tiel-Coder-35B-A3B-Genesis-Hermes-GGUF ornith-ai/Ornith-1.5-35B-A3B · GGUF quantisations | quantisation 20 | mit | 11482 | 2026-08-28 |
| 0bserverx/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored 0bserverx/RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | other | 1021 / 12829 / 594 | 2026-08-31 |
| AngelSlim/Hy4-preview-GGUF AngelSlim/Hy4-preview-GGUF · Hugging Face models | model 2 | — | 292507 | 2026-08-28 |
| mradermacher/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic-NOESIS-BF16-i1-GGUF AMAImedia/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic-NOESIS-BF16 · GGUF quantisations | quantisation 1 | apache-2.0 | 11747 | 2026-09-02 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B deepseek-ai/DeepSeek-R1-Distill-Qwen-14B · Hugging Face models | model 2 | mit | 338761 | 2025-01-20 |
| 3MPER0RR/gemma-4-31b-it-3MPER0RR-abliterated 3MPER0RR/gemma-4-31b-it-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 | 107 / 11163 / 134 | 2026-09-01 |
| facebook/hubert-large-ls960-ft facebook/hubert-large-ls960-ft · Hugging Face models | model 2 | apache-2.0 | 313621 | 2022-03-02 |
| ggml-org/embeddinggemma-300M-GGUF ggml-org/embeddinggemma-300M-GGUF · Hugging Face models | model 1 | — | 296198 | 2025-09-04 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7B deepseek-ai/DeepSeek-R1-Distill-Qwen-7B · Hugging Face models | model 2 | mit | 266017 | 2025-01-20 |
| ApolloRaines/Jenzin-Wuang-Nemotron-30B-A3B-BF16 ApolloRaines/Jenzin-Wuang-Nemotron-30B-A3B-BF16 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | other | 10491 / 1927 / 2406 | 2026-09-02 |
| ATH-MaaS/OvisOCR2 ATH-MaaS/OvisOCR2 · Hugging Face models | model 2 | apache-2.0 | 197760 | 2026-07-13 |
| deepseek-ai/DeepSeek-V2-Lite deepseek-ai/DeepSeek-V2-Lite · Hugging Face models | model 1 | other | 223122 | 2024-05-15 |
| mradermacher/Ornith-1.5-35B-A3B-FULLY-OBLITERATED-GGUF jhone888/Ornith-1.5-35B-A3B-FULLY-OBLITERATED · GGUF quantisations | quantisation 1 | mit | 10021 | 2026-08-30 |
| CohereLabs/cohere-transcribe-03-2026 CohereLabs/cohere-transcribe-03-2026 · Hugging Face models | model 2 | apache-2.0 | 211795 | 2026-03-24 |
| meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers unsloth/GLM-5.3-Flash-GGUF · GGUF quantisations | quantisation 1 | mit | 9729 | 2026-08-28 |
| BDRC/tibetan-ocr BDRC/tibetan-ocr · Hugging Face models | model 2 | apache-2.0 | 134966 | 2026-08-17 |
Facets
Task 1343 of 10489 claims
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