(developers.googleblog.com)

602 points emrah | 1 comments | 20 Apr 25 12:22 UTC | HN request time: 0.203s | source

1. mythz ◴[20 Apr 25 13:46 UTC] No.43743733[source]▶

The speed gains are real, after downloading latest QAT gemma3:27b eval perf is now 1.47x faster on ollama, up from 13.72 to 20.11 tok/s (on A4000's).

Gemma 3 QAT Models: Bringing AI to Consumer GPUs