MLX
Safetensors
qwen3_5_moe
oq
quantized
benchmark
performance
Mixture of Experts
code
agentic-coding
2-bit
Instructions to use mlx-works/KAT-Coder-V2.5-Dev-oQ2e 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-oQ2e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-works/KAT-Coder-V2.5-Dev-oQ2e --local-dir KAT-Coder-V2.5-Dev-oQ2e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
-
Add backup of original chat template
Verified signature5d7aec3 -
Update chat template with Fixed version
Verified signatureee2e711 -
Add model card with benchmark results
Verified signature3fb8d13
-
Upload KAT-Coder-V2.5-Dev-oQ2e via oMLX
Verified signature74ea377 -
initial commit
Verified signature68c77f4