drumih/turbo-fieldfare

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

↗ Open on GitHub

Stars

6,700

Forks

426

Language

Swift

License

Apache-2.0

Last push

3 days ago

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

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.