Instructions to use Lowkey-Loki/reka-flash-3-mlx-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Lowkey-Loki/reka-flash-3-mlx-3bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir reka-flash-3-mlx-3bit Lowkey-Loki/reka-flash-3-mlx-3bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Quantized 3bit MLX version of https://huggingface.co/RekaAI/reka-flash-3
- Downloads last month
- -
Model size
3B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
3-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Lowkey-Loki/reka-flash-3-mlx-3bit
Base model
RekaAI/reka-flash-3