Gemma 3 27B Base
The largest pretrained Gemma 3 checkpoint, combining multimodal input, long context and single-accelerator deployment.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 54.2
Scale and multimodality raise general capability, while base status limits agency. Single-accelerator open deployment creates substantial diffusion and control challenges.
News tied to Gemma 3 27B Base
The model score of 54.2 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Google releases eight Gemma 3 open model checkpoints
Google released Gemma 3 base and instruction-tuned checkpoints at 1B, 4B, 12B and 27B sizes, with multimodal reasoning, long context and broad local and cloud distribution.
- Full item contribution
- +0.14
- Gemma 3 27B Base equal share
- +0.02
Model score history
-
R4
Doom Score 54.2
Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 54.2
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 54.4
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 55.0
Initial exact profile for the separately released 27B base checkpoint.
12 Aug 2026