🎉Qwen-Image-2.1 的 GGUF 量化版来了！极限操作 Mac 8G 可运行 2-bit 模型体积仅 2.47GB。Mac 16G 应该可以考虑4-bit 模型体积仅 4.2GB。可以轻轻松松跑通了。感谢UnslothAI团队的出手！4-bit 重要层动态保留了高精度兼顾画质与效率。
AI少年@aehyok11.3K followers15d ago
0:13Plays on X, where the post was published. Open the original post.
Views on X
19.9KLikes
91Reposts
9Replies
2Post text
🎉Qwen-Image-2.1 的 GGUF 量化版来了！极限操作 Mac 8G 可运行 2-bit 模型体积仅 2.47GB。Mac 16G 应该可以考虑4-bit 模型体积仅 4.2GB。可以轻轻松松跑通了。感谢UnslothAI团队的出手！4-bit 重要层动态保留了高精度兼顾画质与效率。
This entry is part of the launch video directory and the Mac Productivity launch videos. Counts are read from X and refresh every 15 minutes; the video itself stays on X. See the methodology.