rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX

Quantization vs deepseek-ai/DeepSeek-V4.1-Flash. rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse