ormandj/GLM-5.3-Flash-W4A16-NVFP4-K32-Experts-FP8-WO

Quantization vs zai-org/GLM-5.3-Flash-BF16. ormandj/GLM-5.3-Flash-W4A16-NVFP4-K32-Experts-FP8-WO is a quantized version of the other (U8/F8_E4M3).

On the Hub · Downloads on Model Pulse