Modelpublic

soundsgoodai/GLM-4.7-NVFP4-KV-cache-BF16

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

0likes22downloads

Model Card

A quantization setup used for GLM-4.7:

—Weights: NVFP4
—KV cache: BF16
—Tooling: NVIDIA/Model-Optimizer
—Deploy with TensorRT-LLM