Summarization
MLX
Safetensors
qwen3
bodega
inference
on-prem
retrieval
ai-os
vertex
balanced-performance
code-generation
reasoning
router
apple-silicon
privacy-first
8-bit precision
Instructions to use srswti/bodega-vertex-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use srswti/bodega-vertex-4b with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir bodega-vertex-4b srswti/bodega-vertex-4b
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Ctrl+K