INCModel3/DeepSeek-V4.1-Flash-W4A16-Engram-AutoRound

Quantization vs deepseek-ai/DeepSeek-V4.1-Flash. INCModel3/DeepSeek-V4.1-Flash-W4A16-Engram-AutoRound is a quantized version of the other (I32/U8).

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

On the Hub · Downloads on Model Pulse