Gemma 3
Google DeepMind — Gemma
partial detail 15 method fields published
Evaluation
Impact on KV cache memory ablation
balance between model memory and KV cache during inference with a 32k-token pre-fill context, across local:global ratios and sliding window sizes; KV cache memory as a function of context length for the 2B architecture (L:G=5:1, sw=1024) vs a global-only 2B model
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.