Unsloth 将 GLM-5.3 量化至 2-bit，可在 256GB Mac 本地运行
GLM-5.3 can now be run locally!
AI 导读
Unsloth 宣布 GLM-5.3 现已支持本地运行，其 2-bit 量化版本把模型从 1.51TB 压缩到 239GB，体积减少 83%，精度保留约 81%。该版本可在 256GB Mac 或相应 RAM/VRAM 配置上运行，Unsloth 同时放出了使用指南和 GGUF 文件。GLM-5.3 由 Z.ai 开放权重，官方称其面向智能体编码与网络防御。
查看原帖GLM-5.3 is now open-weight. Our most capable model for agentic coding and cyber defense is now available to download, run, and customize. Weights: https://t.co/v1IbWMXxg4 Tech blog: https://t.co/ekQkO83jCv https://t.co/f8XlJksKyf
正文
当前显示原文，中文全文译文尚未就绪。
GLM-5.3 can now be run locally!
The 2-bit model retains ~81% accuracy after we shrunk it from 1.51TB to 239GB (-83% size).
Run on a 256GB Mac or RAM/VRAM setups.
GLM-5.3 is the strongest open model to date.