MLX
Safetensors
qwen3_moe
bodega
inference
on-prem
retrieval
ai-os
axe
turbo
high-performance
code-generation
reasoning
swe-bench
agentic-coding
tool-use
cascade-rl
apple-silicon
privacy-first
8-bit precision
Instructions to use srswti/axe-turbo-31b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use srswti/axe-turbo-31b with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir axe-turbo-31b srswti/axe-turbo-31b
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Ctrl+K