Google logo

Gemma 4 E4B

Multimodal
Google

Gemma 4 E4B is Google DeepMind's compact multimodal model with 4.5 billion effective parameters (8B with embeddings) and a 128K context window. Supports image, text, and audio inputs. Features Per-Layer Embeddings for efficient on-device deployment while maintaining strong multimodal capabilities.

Key Specifications

Parameters
8.0B
Context
131.1K
Release Date
April 2, 2026
Average Score
50.5%

Timeline

Key dates in the model's history
Announcement
April 2, 2026
Last Update
September 10, 2026
Today
September 20, 2026

Technical Specifications

Parameters
8.0B
Training Tokens
-
Knowledge Cutoff
January 1, 2025
Family
-
Capabilities
MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)
$0.02
Output (per 1M tokens)
$0.10
Max Input Tokens
131.1K
Max Output Tokens
131.1K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Reasoning

Logical reasoning and analysis
GPQA
Self-reported
58.6%

Other Tests

Specialized benchmarks
AIME 2026
No toolsSelf-reported
42.5%
BIG-Bench Extra Hard
Self-reported
33.1%
LiveCodeBench v6
Self-reported
52.0%
MathVision
Self-reported
59.5%
MedXpertQA
MMSelf-reported
28.7%
MMLU-Pro
Self-reported
69.4%
MMMLU
Self-reported
76.6%
MMMU-Pro
Self-reported
52.6%
MRCR v2 (8-needle)
128kSelf-reported
25.4%
t2-bench
RetailSelf-reported
57.5%

License & Metadata

License
apache_2_0
Announcement Date
April 2, 2026
Last Updated
September 10, 2026

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.