inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX

Quantization vs deepseek-ai/DeepSeek-V4-Flash-Vision-Exp. inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX is a quantized version of the other (U32/U8).

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

On the Hub · Downloads on Model Pulse