NVIDIA发布优化版GLM-5.2模型，753B参数，1M上下文

NVIDIA just released an optimized GLM-5.2 on Hugging Face

A 753B parameter MoE with 1M context,
quantized to NVFP4 for Blackwell GPUs—
nearly matching FP8 accuracy. https://t.co/tjtk0dVPEW