mlx-community/Qwen2.5-14B-Instruct-1M-4bit

Quantization vs Qwen/Qwen2.5-14B-Instruct-1M. mlx-community/Qwen2.5-14B-Instruct-1M-4bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse