Converted to MLX and quiantized to Q4. Original model https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct .

Downloads last month
3
Safetensors
Model size
1.25B params
Tensor type
F16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jesusoctavioas/Meta-Llama-3.1-8B-Instruct-MLX-Q4

Quantized
(455)
this model