TensorFold/DeepSeek-V4.1-Flash-MLX-2bit-MTP
Quantization vs deepseek-ai/DeepSeek-V4.1-Flash. TensorFold/DeepSeek-V4.1-Flash-MLX-2bit-MTP is a quantized version of the other (U32/BF16).
1 other repos hold byte-for-byte identical weight files.
Quantization vs deepseek-ai/DeepSeek-V4.1-Flash. TensorFold/DeepSeek-V4.1-Flash-MLX-2bit-MTP is a quantized version of the other (U32/BF16).
1 other repos hold byte-for-byte identical weight files.