MLX
Safetensors
qwen3
bodega
inference
on-prem
retrieval
ai-os
raptor
reasoning
ultra-lightweight
edge-deployment
iot
apple-silicon
privacy-first
tool-use
6-bit
Instructions to use srswti/bodega-raptor-0.9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use srswti/bodega-raptor-0.9b with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download srswti/bodega-raptor-0.9b --local-dir bodega-raptor-0.9b
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Ctrl+K