Gemma 3N E2B is an AI model from Google. A Gemma 3N model operating at an effective 2B parameter size for mobile and low-resource multimodal tasks.
Specifications
Canonical IDgoogle-gemma-3n-e2b
StatusActive
CreatorGoogleGoogle
Benchmarks
Intelligence Index
4.8
#469
Coding Index
2.2
#369
Math Index
10.3
#225
MMLU-Pro
0.4
#302
GPQA
0.2
#441
HLE
0.0
#385
LiveCodeBench
0.1
#300
AIME
0.1
#126
IFBench
0.2
#371
Time to First Token
SciCode
0.1
#415
MATH-500
0.7
#131
AIME 2025
0.1
#225
LCR
0.0
#358
TerminalBench Hard
0.0
#323
TAU2
0.0
#370
Output TPS
0.0
#362

Capabilities

Input0/5
Text·
Image·
Audio·
Video·
PDF·
Output0/5
Text·
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemma 4 31BAvailable
Gemma 4 31BAvailable
Gemma 4 26B A4BAvailable
Gemma 4 26B A4BAvailable
Gemma 4 E4BAvailable
Gemma 4 E2BAvailable
Gemma 4 E4BAvailable
Gemma 4 E2BAvailable
Gemma 4Available
Gemma 4 31B IT TurboAvailable
Gemma 3N E2BCurrent

Model IDs