mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-4bit

Quantization vs nvidia/Llama-3.1-Nemotron-70B-Instruct-HF. mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-4bit is a quantized version of the other (U32/F16).

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

On the Hub · Downloads on Model Pulse