MLX
Safetensors
qwen3_moe
causal-lm
Mixture of Experts
mixture-of-experts
qwen
distillation
svd
lora-merged
code-generation
mlx-my-repo
4-bit precision
Instructions to use jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- 667ede42ea99ddb5ec74146ecd884b1f044ac2caf50c2983f4533a5db0078e0e
- Size of remote file:
- 5.28 GB
- SHA256:
- 2fe3c85dd0223c02e2d451897a914a44f54dac412b9613b1ba7e400c9c219531
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.