mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit

Quantization vs deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit is a quantized version of the other (U32/F16).

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

On the Hub · Downloads on Model Pulse