MXFP8量化原理揭秘:NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp8如何把31B模型压缩到30GB
MXFP8量化原理揭秘:NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp8如何把31B模型压缩到30GB 【免费下载链接】NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp8 项目地址: https://ai.gitcode.com/hf_mirrors/mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-m…
2026/8/16 20:31:52