mlx-community/OLMo-2-0325-32B-Instruct-4bit

Quantization vs allenai/OLMo-2-0325-32B-Instruct. mlx-community/OLMo-2-0325-32B-Instruct-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse