axiomofmind/GLM-5.3-Flash-W4A16-NVFP4

Quantization vs zai-org/GLM-5.3-Flash-BF16. axiomofmind/GLM-5.3-Flash-W4A16-NVFP4 is a quantized version of the other (U8/BF16).

1 derivatives checked

• axiomofmind/GLM-5.3-Flash-W4A16-NVFP4-GGUF: Quantization

On the Hub · Downloads on Model Pulse