mlx-community/OLMoE-1B-7B-0125-Instruct-4bit

Quantization vs allenai/OLMoE-1B-7B-0125-Instruct. mlx-community/OLMoE-1B-7B-0125-Instruct-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse