pipenetwork/DeepSeek-V4.1-Flash-MLX-mixed-4_8bit

Quantization vs deepseek-ai/DeepSeek-V4.1-Flash. pipenetwork/DeepSeek-V4.1-Flash-MLX-mixed-4_8bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse