mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit
Quantization vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit is a quantized version of the other (U32/BF16).
1 other repos hold byte-for-byte identical weight files.
Quantization vs deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit is a quantized version of the other (U32/BF16).
1 other repos hold byte-for-byte identical weight files.