mlx-community/Llama-3.2-1B-Instruct-4bit

Quantization vs mlx-community/Llama-3.2-1B-Instruct-bf16. mlx-community/Llama-3.2-1B-Instruct-4bit is a quantized version of the other (U32/F16).

1 derivatives checked

• aniruddhabagal/fraud-sentinel-1b: Partial fine-tune

5 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse