drumih/turbo-fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

⭐ 6.3k ⑂ 378 Swift Apache-2.0 · 10 小时前推送

apple-silicon gemma gemma4 gemma4-26b-a4b gpgpu llm llm-inference local-ai macos metal on-device-ai on-device-llm swift

6.3k

Watchers

0

贡献者

0

Commits

0

Releases

50

Open Issues

10 小时前

最近推送

原文中文

暂无 README