Google DeepMind · Gemma 4

Gemma 4 E4B

READER SUMMARY

Compact Apache-licensed Gemma 4 tier for offline multimodal and local agentic workflows.

DOOM SCORE63.5out of 100model risk profile, not the overall index

CURRENT ASSESSMENT · REVISION 2

Why this model scores 63.5

Stronger edge autonomy combines with near-maximal local distribution, while limited scale constrains the highest-risk capabilities.

Capability67

Autonomy55

Deployment98

Misuse potential45

Control difficulty50

MODEL-ATTRIBUTED EVIDENCE

News tied to Gemma 4 E4B

The model score of 63.5 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.03

Each article's leave-one-out 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 are recalculated from their technical profile and related news, but never feed back into the overall index.

02 Apr 2026DeploymentTOWARD

Google DeepMind releases four Apache-licensed Gemma 4 tiers for local agents

Google DeepMind released four exact Gemma 4 tiers under Apache 2.0 with function calling, multimodal input, local execution, and broad day-one tooling support.

Full item contribution: +0.11
Gemma 4 E4B equal share: +0.03

Read assessment →

AUDIT TRAIL

Model score history

R2
Doom Score 63.5
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026
R1
Doom Score 62.6
New exact tier verified from dated primary launch.
11 Aug 2026