RedHatAI/DeepSeek-V4-Flash-0731-NVFP4

Quantization vs deepseek-ai/DeepSeek-V4-Flash-0731. RedHatAI/DeepSeek-V4-Flash-0731-NVFP4 is a quantized version of the other (U8/F8_E4M3).

On the Hub · Downloads on Model Pulse