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
1–25 of 44| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash-0731 · Hugging Face models, GGUF quantisations | model 2 quantisation 5 | mit / other | 3824182 / 4 / 4494615 / 5862 / 591 / 6392 / 855 | 2026-07-31 |
| Devopsopraiz/Baanzon-Chenni-1.5-9B Devopsopraiz/Baanzon-Chenni-1.5-9B · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 1590 / 4950 / 982 / 999 | 2026-09-07 |
| 3MPER0RR/DeepSeek-R1-Distill-Qwen-32B-3MPER0RR-abliterated 3MPER0RR/DeepSeek-R1-Distill-Qwen-32B-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 2388 / 4718 / 860 / 896 | 2026-09-05 |
| 3MPER0RR/DeepSeek-R1-Distill-Qwen-14B-3MPER0RR-abliterated 3MPER0RR/DeepSeek-R1-Distill-Qwen-14B-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 1321 / 4643 / 465 / 505 | 2026-09-12 |
| dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16 dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 4490 / 6762 / 6775 | 2026-08-30 |
| 3MPER0RR/Ornith1.5-9B-3MPER0RR-abliterated 3MPER0RR/Ornith1.5-9B-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 4 | mit | 1522 / 278 / 3501 / 4283 / 432 / 831 | 2026-08-31 |
| 3MPER0RR/Ornith-1.5-35B-A3B-3MPER0RR-abliterated 3MPER0RR/Ornith-1.5-35B-A3B-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 3 | mit | 1375 / 273 / 3640 / 490 / 508 | 2026-09-16 |
| 3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated 3MPER0RR/DeepSeek-R1-Distill-Llama-8B-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 3 | mit | 1014 / 1949 / 1996 / 3513 / 58 | 2026-09-04 |
| DJLougen/hermes-qwen3.5-35b-a3b-GGUF DJLougen/hermes-qwen3.5-35b-a3b-GGUF · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | apache-2.0 / mit | 3181 / 3690 / 4375 | 2026-03-31 |
| 3MPER0RR/GLM-4.6V-Flash-3MPER0RR-abliterated 3MPER0RR/GLM-4.6V-Flash-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 2693 / 546 / 578 / 701 | 2026-09-19 |
| ai-sage/GigaChat3.5-432B-A28B-Reasoning-bf16 ai-sage/GigaChat3.5-432B-A28B-Reasoning-bf16 · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 135 / 2094 / 472 / 534 | 2026-09-03 |
| dealignai/GLM-5.3-UNCENSORED-FP8 dealignai/GLM-5.3-UNCENSORED-FP8 · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1715 / 2632 / 2729 | 2026-08-30 |
| ArliAI/GLM-4.5-Air-Derestricted ArliAI/GLM-4.5-Air-Derestricted · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1282 / 148 / 177 | 2025-11-24 |
| BlossomsAI/Qwen2.5-Coder-7B-Instruct-Uncensored BlossomsAI/Qwen2.5-Coder-7B-Instruct-Uncensored · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1230 / 620 / 823 | 2024-12-26 |
| ai-sage/GigaChat3-10B-A1.8B-base ai-sage/GigaChat3-10B-A1.8B-base · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1077 / 224 / 236 | 2025-11-19 |
| deepgrove/maple-preview deepgrove/maple-preview · Hugging Face models, GGUF quantisations | model 2 quantisation 3 | mit | 2568 / 2572 / 36 / 650 / 976 | 2026-08-04 |
| CMSManhattan/JiRackDeltaNet_27b CMSManhattan/JiRackDeltaNet_27b · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 551790 / 553715 / 664 | 2026-08-29 |
| CodeDevX/auralis-coder CodeDevX/auralis-coder · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 576 / 720 / 767 | 2026-09-11 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B · Hugging Face models, GGUF quantisations | model 2 quantisation 9 | apache-2.0 / mit | 126 / 160 / 161 / 166 / 169 / 35 / 38 / 470297 / 538 / 78 / 954847 | 2025-01-20 |
| BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1139 / 457 / 491 | 2025-01-30 |
| GestaltLabs/DeepSeek-V4-Flash-0731-Ornstein GestaltLabs/DeepSeek-V4-Flash-0731-Ornstein · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | mit | 400 / 438 | 2026-09-08 |
| deepseek-ai/DeepSeek-V4-Flash deepseek-ai/DeepSeek-V4-Flash · Hugging Face models, GGUF quantisations | model 2 quantisation 2 | mit | 1099375 / 1307475 / 229 / 385 | 2026-04-22 |
| castorini/rank_zephyr_7b_v1_full castorini/rank_zephyr_7b_v1_full · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 351 / 5995 / 6026 | 2024-01-19 |
| benni-ben/Rogue-HH-Instruct benni-ben/Rogue-HH-Instruct · Hugging Face models, GGUF quantisations | model 1 quantisation 1 | mit | 306 / 734 | 2026-09-25 |
| deepseek-ai/DeepSeek-V4-Flash-DSpark deepseek-ai/DeepSeek-V4-Flash-DSpark · Hugging Face models, GGUF quantisations | model 2 quantisation 1 | mit | 1013784 / 242 / 814665 | 2026-06-27 |
Facets
Licence 8160 of 10579 claims
mit718
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