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
51–75 of 2,276| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| XingChen-AGI/Xing4.0-29B-A4B-GGUF · GGUF quantisations | quantisation 1 | apache-2.0 | 16028 | 2026-09-16 |
| NANI-Nithin/K2-Horizon-3.7B-GGUF IFM/K2-Horizon-3.7B · GGUF quantisations | quantisation 7 | apache-2.0 | 11474 | 2026-09-03 |
| mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic-v2-i1-GGUF OS-Software/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic-v2 · GGUF quantisations | quantisation 3 | apache-2.0 | 15418 | 2026-09-08 |
| atakhadivi/Qwen3.8-2B-Uncensored-GGUF empero-ai/Qwen3.8-2B · GGUF quantisations | quantisation 3 | apache-2.0 | 15373 | 2026-08-27 |
| atakhadivi/Qwen3.8-2B-Uncensored-GGUF Qwen/Qwen3.5-2B · GGUF quantisations | quantisation 36 | apache-2.0 | 0 | 2026-08-27 |
| WaveCut/Qwen3.8-27B-GSQ-RCO-IQ3_S-NInfer-v3 ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF · GGUF quantisations | quantisation 6 | apache-2.0 | 13734 | 2026-08-31 |
| WaveCut/Qwen3.8-27B-GSQ-RCO-IQ3_S-NInfer-v3 z-lab/Qwen3.8-27B-DFlash2 · GGUF quantisations | quantisation 4 | apache-2.0 | 14672 | 2026-09-04 |
| DrMoriarty0/Qwen_Qwen3.6-35B-A3B-GGUF Qwen/Qwen3.6-35B-A3B · GGUF quantisations | quantisation 42 | apache-2.0 | 110 | 2026-08-30 |
| ngquocvinh/AliceAI-T5-35B-A0.6B-GGUF yandex/AliceAI-T5-35B-A0.6B · GGUF quantisations | quantisation 1 | apache-2.0 | 13584 | 2026-09-14 |
| audio-cpp/LiveAvatar-GGUF Wan-AI/Wan2.2-S2V-14B · GGUF quantisations | quantisation 1 | apache-2.0 | 13422 | 2026-09-18 |
| SpeakoFlow/speakoflow-mini Qwen/Qwen3.5-0.8B · GGUF quantisations | quantisation 45 | apache-2.0 | 0 | 2026-08-28 |
| christopherthompson81/MOSS-TTS-v1.5-GGUF OpenMOSS-Team/MOSS-TTS-v1.5 · GGUF quantisations | quantisation 1 | apache-2.0 | 12710 | 2026-09-21 |
| christopherthompson81/MOSS-TTS-v1.5-GGUF OpenMOSS-Team/MOSS-Audio-Tokenizer · GGUF quantisations | quantisation 2 | apache-2.0 | 12710 | 2026-09-21 |
| ManniX-ITA/JackOD-9B-Coder-MTP-GGUF ManniX-ITA/JackOD-9B-Coder · GGUF quantisations | quantisation 3 | apache-2.0 | 1037 | 2026-09-11 |
| mradermacher/G4-MeroMero-v2-31B-heretic-i1-GGUF DogOnKeyboard/G4-MeroMero-v2-31B-heretic · GGUF quantisations | quantisation 2 | apache-2.0 | 12702 | 2026-09-09 |
| EldanRing/Winnow-12B google/gemma-4-12B-it · GGUF quantisations | quantisation 30 | apache-2.0 | 1072 | 2026-08-27 |
| ccharnkij/gpt-oss-120b-Uncensored ccharnkij/gpt-oss-120b-Uncensored · Hugging Face models, GGUF quantisations | model 1 quantisation 2 | apache-2.0 | 12018 / 319 / 668 | 2026-09-26 |
| mradermacher/Qwen3.5-9B-Kimi-k3-Distilled-i1-GGUF khazarai/Qwen3.5-9B-Kimi-k3-Distilled · GGUF quantisations | quantisation 3 | apache-2.0 | 11875 | 2026-09-16 |
| fallentree/Qwen3.8-27B-Uncensored-GP100-GGUF JonathanColetti/Qwen3.8-27B-Uncensored · GGUF quantisations | quantisation 6 | apache-2.0 | 1155 | 2026-08-27 |
| fallentree/Qwen3.8-27B-Uncensored-GP100-GGUF mradermacher/Qwen3.8-27B-Uncensored-i1-GGUF · GGUF quantisations | quantisation 1 | apache-2.0 | 11852 | 2026-09-04 |
| fallentree/Qwen3.8-27B-Uncensored-GP100-GGUF incoai/Qwen3.8-27B-DFlash2 · GGUF quantisations | quantisation 4 | apache-2.0 | 11852 | 2026-08-27 |
| 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 2 | apache-2.0 | 11747 | 2026-09-02 |
| Cyclone-Labs/Twilight-Embrace-31B Cyclone-Labs/Twilight-Embrace-31B · Hugging Face models, GGUF quantisations | model 1 quantisation 2 | apache-2.0 | 11389 / 2064 / 44 | 2026-09-23 |
| mradermacher/Gemma-4-E4B-Abliterated-Uncensored-i1-GGUF Madras1/Gemma-4-E4B-Abliterated-Uncensored · GGUF quantisations | quantisation 2 | apache-2.0 | 11387 | 2026-09-06 |
| bartowski/Gryphe_Pantheon-Reasoning-26B-A4B-1.1-V2-GGUF Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2 · GGUF quantisations | quantisation 5 | apache-2.0 | 11361 | 2026-09-08 |
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