flukethoughts/GLM-4.5-Architect-106B-A12B-NVFP4

Quantization vs ConicCat/GLM-4.5-Architect-106B-A12B. flukethoughts/GLM-4.5-Architect-106B-A12B-NVFP4 is a quantized version of the other (U8/BF16).

On the Hub · Downloads on Model Pulse