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 |
|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Flash-Vision-Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 36695 / 62318 / 925431 / 951084 | 2026-08-31 |
| llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved · GGUF quantisations | quantisation 2 | apache-2.0 | 21192 | 2026-08-30 |
| WalkingCat/Soprano-1.1-80M-GGUF · GGUF quantisations | quantisation 1 | apache-2.0 | 54076 | 2026-08-27 |
| llmfan46/LongCat-Flash-Lite-Sparse-Ultra-Uncensored-Heretic-Native-MTP-And-LSA-Preserved-GGUF llmfan46/LongCat-Flash-Lite-Sparse-Ultra-Uncensored-Heretic-Native-MTP-And-LSA-Preserved · GGUF quantisations | quantisation 1 | mit | 53518 | 2026-08-29 |
| 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF · Hugging Face models | model 1 | apache-2.0 | 1410392 | 2026-08-14 |
| Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF · GGUF quantisations | quantisation 1 | — | 40613 | 2026-08-28 |
| deepseek-ai/DeepSeek-V4-Flash deepseek-ai/DeepSeek-V4-Flash · Hugging Face models | model 2 | mit | 1099375 | 2026-04-22 |
| dealignai/GLM-5.3-Flash-UNCENSORED-FP8 dealignai/GLM-5.3-Flash-UNCENSORED-FP8 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 38203 / 47360 / 47456 | 2026-08-26 |
| circlestone-labs/Anima circlestone-labs/Anima · Hugging Face models | model 2 | other | 1186688 | 2026-01-29 |
| inclusionAI/Ling-3.0-tiny-GGUF · GGUF quantisations | quantisation 1 | mit | 37304 | 2026-08-30 |
| apple/OpenELM-1_1B-Instruct apple/OpenELM-1_1B-Instruct · Hugging Face models | model 2 | apple-amlr | 1204778 | 2024-04-12 |
| jcbtc/Qwen3.8-Flash-CIRU-STRIX-IU4 Qwen/Qwen3.8-Flash-Next-FP8 · GGUF quantisations | quantisation 1 | other | 36040 | 2026-08-29 |
| amazon/chronos-t5-small amazon/chronos-t5-small · Hugging Face models | model 2 | apache-2.0 | 1064253 | 2024-02-21 |
| jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUF HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive · GGUF quantisations | quantisation 1 | apache-2.0 | 35283 | 2026-09-01 |
| jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUF LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Final-GGUF · GGUF quantisations | quantisation 1 | apache-2.0 | 35283 | 2026-09-01 |
| ggml-org/Qwen3.8-27B-GGUF ggml-org/Qwen3.8-27B-GGUF · Hugging Face models | model 1 | apache-2.0 | 1075427 | 2026-08-14 |
| orcarouter/GLM-5.3-Flash-Uncensored-GGUF zai-org/GLM-5.3-Flash · GGUF quantisations | quantisation 1 | mit | 32465 | 2026-08-31 |
| dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8 dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 / other | 1170 / 1503 / 32460 | 2026-08-27 |
| dots-studio/dots.ocr dots-studio/dots.ocr · Hugging Face models | model 2 | mit | 1013742 | 2025-07-30 |
| deepseek-ai/DeepSeek-V4-Flash-DSpark deepseek-ai/DeepSeek-V4-Flash-DSpark · Hugging Face models | model 2 | mit | 1013784 | 2026-06-27 |
| audio-cpp/VibeVoice-7B-GGUF vibevoice/VibeVoice-7B · GGUF quantisations | quantisation 1 | mit | 28476 | 2026-08-28 |
| deepseek-ai/DeepSeek-R1 deepseek-ai/DeepSeek-R1 · Hugging Face models | model 1 | mit | 968888 | 2025-01-20 |
| mradermacher/Qwen3.8-14B-Instruct-Turbo-GGUF ewinregirgojr/Qwen3.8-14B-Instruct-Turbo · GGUF quantisations | quantisation 1 | apache-2.0 | 27066 | 2026-08-29 |
| js-byte/Audio8-TTS-Preview-0.6b-GGUF Audio8/Audio8-TTS-Preview-0.6b · GGUF quantisations | quantisation 1 | apache-2.0 | 26800 | 2026-08-31 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B · Hugging Face models | model 2 | mit | 470297 | 2025-01-20 |
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