Hugging Bay Publishers
Browse publisher namespaces and public catalog metadata.
Publisher launch kit · Apply for namespace
Downloadable doesn't mean tested: this record says whether the exact file can be downloaded now, not that the model is complete or that it runs.
Showing stale catalog ·
| Type | Model | Recorded size | Downloads | Updated |
|---|---|---|---|---|
Ternary Bonsai 27Bprism-ml/Ternary-Bonsai-27B-ggufThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: prism-ml on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 86.5 GB | 697,666 downloads on Hugging Face | 2026-08-31 | |
Qwen3.8 27B Unleashedoutsourc-e/Qwen3.8-27B-Unleashed-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: outsourc-e on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 123 GB | 43,406 downloads on Hugging Face | 2026-08-21 | |
Seed OSS 36B MLX 5bitlmstudio-community/Seed-OSS-36B-Instruct-MLX-5bitThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: lmstudio-community on Hugging Face. File format: Safetensors.
| 24.9 GB | 31,612 downloads on Hugging Face | 2026-09-18 | |
Qwen3.8 27B EfficientThink Uncensored K3 Opus5 Grok4.6 GPT5.6Sol SFT SimPO DFlash2nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: nerkyor on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 176.5 GB | 28,899 downloads on Hugging Face | 2026-09-08 | |
Qwen3.8 27B Heretic Uncensored Q5 K Mmlasli/Qwen3.8-27B-Heretic-Uncensored-Q5_K_M-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: mlasli on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 19.7 GB | 24,679 downloads on Hugging Face | 2026-09-17 | |
Ternary Bonsai 2 27B Abliterated PTQ1 0BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: uploader describes removal; not independently verified.DetailsThe catalog lists this model for having conversations.Source: BoldingBuilds on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 5.95 GB | 16,863 downloads on Hugging Face | 2026-09-23 | |
zai org GLM 4.7 Flashbartowski/zai-org_GLM-4.7-Flash-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: bartowski on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.5 GB | 10,252 downloads on Hugging Face | 2026-01-21 | |
Gemma 4 31B Abliterated Uncensored i1mradermacher/Gemma-4-31B-Abliterated-Uncensored-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: uploader describes removal; not independently verified.DetailsThe catalog lists this model for having conversations.Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 9,324 downloads on Hugging Face | 2026-09-18 | |
Qwen2.5 Coder 32Blmstudio-community/Qwen2.5-Coder-32B-GGUFThe catalog lists this model for working with code. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for working with code.Source: lmstudio-community on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 19.9 GB | 9,285 downloads on Hugging Face | 2024-11-11 | |
Tencent Hy 30B A3B uncensored heretic i1mradermacher/Tencent-Hy-30B-A3B-uncensored-heretic-i1-GGUFThe catalog lists this model for translating text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for translating text.Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.2 GB | 8,382 downloads on Hugging Face | 2026-09-17 | |
Ornith 1.5 35B A3B Uncensored i1mradermacher/Ornith-1.5-35B-A3B-Uncensored-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 21.7 GB | 6,566 downloads on Hugging Face | 2026-09-18 | |
gemma 4 31B it Mystery Fine Tune HERETIC UNCENSORED Thinking i1mradermacher/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-i1-GGUFThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 4,323 downloads on Hugging Face | 2026-06-30 | |
allura org Q3 30B A3B Designantbartowski/allura-org_Q3-30B-A3B-Designant-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: bartowski on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.6 GB | 3,827 downloads on Hugging Face | 2026-09-17 | |
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU MTP i1mradermacher/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-i1-GGUFThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 16.8 GB | 3,512 downloads on Hugging Face | 2026-09-18 | |
Qwen3.8 27B Uncensored NOESIS BF16 i1mradermacher/Qwen3.8-27B-Uncensored-NOESIS-BF16-i1-GGUFThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 16.8 GB | 3,251 downloads on Hugging Face | 2026-09-18 | |
Darkhn M3.2 36B Animus V12.0 Heretic Uncensored i1alexokita/Darkhn-M3.2-36B-Animus-V12.0-Heretic-Uncensored-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: alexokita on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 21 GB | 2,824 downloads on Hugging Face | 2026-09-17 | |
Mistral Small 3.1 24Bunsloth/Mistral-Small-3.1-24B-Instruct-2503The catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: unsloth on Hugging Face. File format: Safetensors.
| 48 GB | 2,095 downloads on Hugging Face | 2026-09-18 | |
Qwen3.5 35B A3B Uncensored HauhauCS Aggressive MTPAIOpsInSpace/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-MTPThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: AIOpsInSpace on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 21.2 GB | 1,504 downloads on Hugging Face | 2026-09-18 | |
Gemma 4 Queen 31B it uncensored heretic i1mradermacher/Gemma-4-Queen-31B-it-uncensored-heretic-i1-GGUFThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 1,262 downloads on Hugging Face | 2026-09-18 | |
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU MTPmradermacher/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-GGUFThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 16.8 GB | 1,258 downloads on Hugging Face | 2026-09-18 | |
Dolphin3.0 Mistral 24Bdphn/Dolphin3.0-Mistral-24BThe catalog lists this model for having conversations. Catalog sources: publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: dphn on Hugging Face. File format: Safetensors.
| 47.1 GB | 1,136 downloads on Hugging Face | 2026-09-20 | |
Qwen3.8 27B Uncensored JoyFox Aggressive i1mradermacher/Qwen3.8-27B-Uncensored-JoyFox-Aggressive-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 16.8 GB | 1,093 downloads on Hugging Face | 2026-09-18 | |
gemma 4 31B it Grand Horror X INTENSE HERETIC UNCENSORED Thinking i1mradermacher/gemma-4-31B-it-Grand-Horror-X-INTENSE-HERETIC-UNCENSORED-Thinking-i1-GGUFThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 711 downloads on Hugging Face | 2026-09-18 | |
SuperQwen3.8 27B abliteratedJiunsong/SuperQwen3.8-27b-abliteratedThe catalog lists this model for generating text from images and text. Catalog sources: license label, task label.Content controls: uploader describes removal; not independently verified.DetailsThe catalog lists this model for generating text from images and text.See the publisher’s description →Source: Jiunsong on Hugging Face. File format: Safetensors.
| 55.6 GB | 694 downloads on Hugging Face | 2026-08-25 | |
qwen agentworld 35BAtomicChat/qwen-agentworld-35b-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: AtomicChat on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 21.2 GB | 269 downloads on Hugging Face | 2026-09-18 | |
ThinkingCap Qwen3.6 27B Q4 K MAbiray/ThinkingCap-Qwen3.6-27B-Q4_K_M-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Abiray on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 16.8 GB | 227 downloads on Hugging Face | 2026-09-17 | |
Artemis 31B v1fBeaverAI/Artemis-31B-v1f-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 210 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1cBeaverAI/Artemis-31B-v1c-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 203 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1jBeaverAI/Artemis-31B-v1j-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 172 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1eBeaverAI/Artemis-31B-v1e-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 171 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1d GGUF BROKENBeaverAI/Artemis-31B-v1d-GGUF-BROKENThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 165 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1gBeaverAI/Artemis-31B-v1g-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 155 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1iBeaverAI/Artemis-31B-v1i-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 154 downloads on Hugging Face | 2026-09-18 | |
Huihui Qwen3.5 35B A3B Claude 4.6 Opus abliterated i1mradermacher/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: uploader describes removal; not independently verified.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 21.2 GB | 154 downloads on Hugging Face | 2026-09-18 | |
Qwen3.5 27B ultra uncensored heretic v1 i1mradermacher/Qwen3.5-27B-ultra-uncensored-heretic-v1-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 16.5 GB | 133 downloads on Hugging Face | 2026-09-19 | |
Qwen3.5 35B A3B heretic v1 i1mradermacher/Qwen3.5-35B-A3B-heretic-v1-i1-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 21.2 GB | 63 downloads on Hugging Face | 2026-09-19 | |
Oni Mitsubishi 12BSicariusSicariiStuff/Oni_Mitsubishi_12BThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: SicariusSicariiStuff on Hugging Face. File format: Safetensors.
| 23.5 GB | 61 downloads on Hugging Face | 2026-09-20 | |
Skyfall R1 31B v4bBeaverAI/Skyfall-R1-31B-v4b-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 19 GB | 47 downloads on Hugging Face | 2026-09-17 | |
Skyfall 31B v4nBeaverAI/Skyfall-31B-v4n-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 19 GB | 46 downloads on Hugging Face | 2026-09-19 | |
Huihui InternVL3 5 30B A3B abliteratedmradermacher/Huihui-InternVL3_5-30B-A3B-Instruct-abliterated-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: uploader describes removal; not independently verified.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: mradermacher on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.6 GB | 43 downloads on Hugging Face | 2026-09-18 | |
Agnes 3.0 FlashAgnes-AI/Agnes-3.0-FlashThe catalog lists this model for generating text from images and text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for generating text from images and text.See the publisher’s description →Source: Agnes-AI on Hugging Face.
| 66.2 GB | 34 downloads on Hugging Face | 2026-09-16 | |
Big Tiger Gemma 27B v1bBeaverAI/Big-Tiger-Gemma-27B-v1b-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 19.4 GB | 33 downloads on Hugging Face | 2026-09-18 | |
Virtuoso Medium v2 6bitarcee-ai/Virtuoso-Medium-v2-6bit-mlxThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: arcee-ai on Hugging Face. File format: Safetensors.
| 26.6 GB | 14 downloads on Hugging Face | 2026-09-20 | |
MediumAGI Q4 K MGuilherme34/MediumAGI-Q4_K_M-GGUFThe catalog lists this model for working with code. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for working with code.Source: Guilherme34 on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 19.9 GB | 11 downloads on Hugging Face | 2026-09-18 | |
KoboldAI OPT 30B Erebus FP8SicariusSicariiStuff/KoboldAI_OPT-30B-Erebus_FP8The catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: SicariusSicariiStuff on Hugging Face. File format: Safetensors.
| 30.4 GB | 5 downloads on Hugging Face | 2026-09-19 | |
DeepSeek V4 Flash Vision Expunsloth/DeepSeek-V4-Flash-Vision-Exp-GGUFThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.See the publisher’s description →Source: unsloth on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 1.16 TB | 0 downloads on Hugging Face | 2026-09-09 | |
Muse Glimmer 30Bunsloth/Muse-Glimmer-30B-GGUFThe catalog lists this model for generating text from images and text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for generating text from images and text.See the publisher’s description →Source: unsloth on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 317 GB | 0 downloads on Hugging Face | 2026-08-10 | |
Huihui DeepSeek V4 Flash 0731 abliteratedhuihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUFThe catalog lists this model for generating text. Catalog sources: license label, task label.Content controls: uploader describes removal; not independently verified.DetailsThe catalog lists this model for generating text.Source: huihui-ai on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 549.3 GB | 0 downloads on Hugging Face | 2026-08-03 | |
Qwen Image Edit 2509unsloth/Qwen-Image-Edit-2509-GGUFThe catalog lists this model for transforming images. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transforming images.See the publisher’s description →Source: unsloth on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 13.1 GB | 3,235 downloads on Hugging Face | 2026-09-18 | |
Artemis 31B v1kBeaverAI/Artemis-31B-v1k-GGUFThe catalog lists this model for having conversations. Catalog sources: publisher tags.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: BeaverAI on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 18.7 GB | 147 downloads on Hugging Face | 2026-09-18 |