Model Card for Model ID

This model its a conversion a quantization of Llama-3.2-1B-Instruct using mlx. For reference https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct .

Model Details

Downloads last month
4
Safetensors
Model size
193M 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/Llama-3.2-1B-Instruct-MLX-Q4

Quantized
(295)
this model