MLX
Safetensors
qwen3_5_moe
oq
quantized
benchmark
performance
mtp
Mixture of Experts
code
agentic-coding
4-bit precision
Instructions to use mlx-works/KAT-Coder-V2.5-Dev-oQ4e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-works/KAT-Coder-V2.5-Dev-oQ4e-mtp with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-works/KAT-Coder-V2.5-Dev-oQ4e-mtp --local-dir KAT-Coder-V2.5-Dev-oQ4e-mtp
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
-
Restore original chat template backup
Verified signature8249dc4 -
Add backup of original chat template
Verified signaturecda194c -
Update chat template with Fixed version
Verified signaturec0b7bb1 -
Add model card with benchmark results
Verified signature0529212 -
Upload KAT-Coder-V2.5-Dev-oQ4e-mtp via oMLX
Verified signature9f5c8b2 -
initial commit
Verified signature3e209ad