Huffing Face

Models. Inhaled.

A very fast mirror of the open-weights models you were going to download anyway. Same files, same checksums, same tools — just closer.

$ export HF_ENDPOINT=https://huffingface.co

That's it. That's the integration. transformers, huggingface_hub, hf — they all just work, only faster. Anything we haven't huffed yet transparently comes from the source.

83 models
19.11 TB huffed
1 huffs served
40 Gbps of exhale
ModelLicenseSizeHuffsStatus
Qwen/Qwen3-8Bapache-2.016.4 GB1fully huffed
thinkingmachines/Inklingapache-2.01.90 TB0fully huffed
0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUFapache-2.01.62 TB0fully huffed
moonshotai/Kimi-K3kimi-k31.56 TB0fully huffed
zai-org/GLM-5.2mit1.51 TB0fully huffed
bartowski/Qwen_Qwen3-Next-80B-A3B-Thinking-GGUFapache-2.01.15 TB0fully huffed
deepseek-ai/DeepSeek-V4-Promit864.7 GB0fully huffed
zai-org/GLM-5.2-FP8mit755.7 GB0fully huffed
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUFapache-2.0634.9 GB0fully huffed
bartowski/Qwen_Qwen3.6-35B-A3B-GGUFapache-2.0608.3 GB0huffing…
bartowski/Qwen_Qwen3.5-35B-A3B-GGUFapache-2.0605.2 GB0fully huffed
tencent/Hy3apache-2.0597.6 GB0fully huffed
moonshotai/Kimi-K2.7-Codemodified-mit595.2 GB0fully huffed
unsloth/Qwen3.6-35B-A3B-GGUFapache-2.0550.3 GB0fully huffed
unsloth/Qwen3.6-35B-A3B-MTP-GGUFapache-2.0531.4 GB0fully huffed
unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFapache-2.0506.4 GB0huffing…
unsloth/Qwen3.8-27B-GGUFapache-2.0472.1 GB0fully huffed
nvidia/GLM-5.2-NVFP4mit464.9 GB0fully huffed
unsloth/Qwen3.6-27B-MTP-GGUFapache-2.0434.3 GB0fully huffed
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUFapache-2.0424.1 GB0fully huffed
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressiveapache-2.0247.4 GB0fully huffed
OBLITERATUS/Qwen3.8-27B-OBLITERATEDapache-2.0239.7 GB0fully huffed
JonathanColetti/Qwen3.8-27B-Uncensored-GGUFapache-2.0231.3 GB0fully huffed
openai/gpt-oss-120bapache-2.0195.8 GB0fully huffed
open-gigaai/Giga-World-1apache-2.0178.9 GB0fully huffed
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFapache-2.0172.5 GB0fully huffed
deepseek-ai/DeepSeek-V4-Flashmit159.6 GB0fully huffed
unsloth/Qwen3.5-9B-GGUFapache-2.0147.8 GB0fully huffed
unsloth/Qwen3-VL-8B-Instruct-GGUFapache-2.0142.9 GB0fully huffed
Qwen/Qwen3-32B-GGUFapache-2.0127.3 GB0fully huffed
Qwen/Qwen3-30B-A3B-GGUFapache-2.0118.9 GB0fully huffed
ggml-org/Qwen3.8-27B-GGUFapache-2.0113.7 GB0fully huffed
empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUFapache-2.096.2 GB0fully huffed
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUFapache-2.081.4 GB0fully huffed
bartowski/Qwen_Qwen3.5-4B-GGUFapache-2.077.1 GB0fully huffed
mradermacher/Qwen3-VL-8B-Instruct-abliterated-GGUFapache-2.075.3 GB0fully huffed
Qwen/Qwen3.6-35B-A3Bapache-2.071.9 GB0fully huffed
deepreinforce-ai/Ornith-1.0-35Bmit70.3 GB0fully huffed
lmstudio-community/Qwen3.8-27B-GGUFapache-2.069.2 GB0fully huffed
Qwen/Qwen3-32Bapache-2.065.5 GB0fully huffed
Qwen/Qwen3-14B-GGUFapache-2.057.6 GB0fully huffed
Qwen/Qwen3.6-27Bapache-2.055.6 GB0fully huffed
AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUFapache-2.042.7 GB0fully huffed
openai/gpt-oss-20bapache-2.041.3 GB0fully huffed
bartowski/Qwen_Qwen3.5-2B-GGUFapache-2.036.7 GB0fully huffed
Qwen/Qwen3-VL-8B-Instruct-GGUFapache-2.032.0 GB0fully huffed
Qwen/Qwen3-8B-GGUFapache-2.032.0 GB0fully huffed
Qwen/Qwen3.8-27B-FP8apache-2.030.9 GB0fully huffed
mistralai/Mistral-7B-Instruct-v0.3apache-2.029.0 GB0fully huffed
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-GGUFmit24.9 GB0fully huffed
empero-ai/Qwen3.8-4B-Distill-GGUFapache-2.022.8 GB0fully huffed
lmstudio-community/Qwen3-VL-8B-Instruct-GGUFapache-2.021.6 GB0fully huffed
cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUFapache-2.018.1 GB0fully huffed
Qwen/Qwen3-8B-Baseapache-2.016.4 GB0fully huffed
microsoft/TRELLIS.2-4Bmit16.2 GB0fully huffed
athena2634/TRELLIS.2-4Bmit16.2 GB0fully huffed
deepseek-ai/DeepSeek-R1-Distill-Llama-8Bmit16.1 GB0fully huffed
Qwen/Qwen3-4B-GGUFapache-2.015.8 GB0fully huffed
Qwen/Qwen2.5-7B-Instructapache-2.015.2 GB0fully huffed
deepseek-ai/DeepSeek-R1-Distill-Qwen-7Bmit15.2 GB0fully huffed
bartowski/Qwen_Qwen3.5-0.8B-GGUFapache-2.015.1 GB0fully huffed
empero-ai/Qwen3.8-2B-Distill-GGUFapache-2.010.3 GB0fully huffed
Qwen/Qwen3-4Bapache-2.08.1 GB0fully huffed
baidu/Unlimited-OCRmit6.8 GB0fully huffed
BAAI/bge-m3mit4.6 GB0fully huffed
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoiceapache-2.04.5 GB0fully huffed
sentence-transformers/all-mpnet-base-v2apache-2.03.8 GB0fully huffed
google-bert/bert-base-uncasedapache-2.03.5 GB0fully huffed
Qwen/Qwen2.5-1.5B-Instructapache-2.03.1 GB0fully huffed
BAAI/bge-reranker-v2-m3apache-2.02.3 GB0fully huffed
nomic-ai/nomic-embed-text-v1.5apache-2.02.2 GB0fully huffed
openbmb/MiniCPM5-1Bapache-2.02.2 GB0fully huffed
lightonai/LightOnOCR-2-1Bapache-2.02.0 GB0fully huffed
OpenMOSS-Team/MOSS-Transcribe-Diarizeapache-2.01.8 GB0fully huffed
Qwen/Qwen3-0.6Bapache-2.01.5 GB0fully huffed
BAAI/bge-base-en-v1.5mit1.3 GB0fully huffed
Qwen/Qwen3-Embedding-0.6Bapache-2.01.2 GB0fully huffed
Qwen/Qwen2.5-0.5B-Instructapache-2.0999.6 MB0fully huffed
sentence-transformers/all-MiniLM-L6-v2apache-2.0976.9 MB0fully huffed
Qwen/Qwen3-0.6B-GGUFapache-2.0639.5 MB0fully huffed
prism-ml/Bonsai-1.7B-ggufapache-2.0496.7 MB0fully huffed
BAAI/bge-small-en-v1.5mit401.1 MB0fully huffed
hexgrad/Kokoro-82Mapache-2.0363.3 MB0fully huffed

81 of 83 fully local.

Request a model

If its license lets us redistribute it, your request primes the mirror for everyone.

Huffing Face — fast, HF-compatible open-weights model mirror