What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally?
We've open-sourced a demo letting you run multiple models side-by-side on your hardware.
Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.
@plahteenlahti@YsfOmari If I had known, I would’ve put more effort into the video than the app itself 😅 I literally recorded it just two hours before the deadline.
Judging for #Shipyard2026 is underway, and we've already seen some great submissions 🎉
As a reminder, here's the key dates and what's happening:
✅ Submission requirement check
👀 Judging panel review
🏅 Testing + shortlisting
🏆 Creators have the final pick
We'll announce the winner on Thursday, February 26th. See you then!