Unsloth AI· @UnslothAI · X·· 2026-08-29精选AI 评分77
AI 导读
Unsloth 发布 GLM-5.3 的动态 GGUF 量化版本,2-bit 模型从 1.51TB 压缩到 239GB(缩小 83%),保留约 81% top-1 准确率,1-bit 则以缩小 85% 达到约 76%。
推荐理由
原文给出动态量化的精度与体积数据和不同位宽的硬件需求,读者可据此选择本地运行 GLM-5.3 的方案。
正文 · 原文
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.
Guide: https://unsloth.ai/docs/models/glm-5.3
GGUF: https://huggingface.co/unsloth/GLM-5.3-GGUF
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://huggingface.co/zai-org/GLM-5.3 Tech blog: https://z.ai/blog/glm-5.3在 X 查看被引用的帖子
来源:Unsloth AI · x.com