Skip to content

Evaluation

GQA versus MHA ablation

two 9B instances with Multi-Head Attention (MHA) vs Grouped-Query Attention (GQA), compared over several benchmarks

Other documented tests Google DeepMind — Gemma

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemma 2
Google DeepMind — Gemma

partial detail 17 method fields published

See how this test was run