OpensourceWTF/DeepSeek-V4.1-Flash-streaming-repack-exl3-3.0bpw

Quantization vs deepseek-ai/DeepSeek-V4.1-Flash. OpensourceWTF/DeepSeek-V4.1-Flash-streaming-repack-exl3-3.0bpw is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse