Hacker News new | ask | show | jobs
Show HN: Gemma 3 inference in pure C++ with Metal acceleration (github.com)
6 points by ybubnov 27 days ago
1 comments

Looks really cool, thank you. I can't find anything about performance. Is it faster? Or is it just a cool demo?
That’s in my short list of next things to do. In the recent releases my primary focus was on compact size of the executable and modern C++ API.