m1rkocasu/LLaDA2.1-flash-NVFP4-W4A16

Quantization vs inclusionAI/LLaDA2.1-flash. m1rkocasu/LLaDA2.1-flash-NVFP4-W4A16 is a quantized version of the other (U8/F8_E4M3).

On the Hub · Downloads on Model Pulse