Google

Gemma 3n E2B Instructed LiteRT (Preview)

Multimodal
Zero-eval

by Google

+
+
+
+
About

Gemma 3N E2B IT LiteRT Preview was introduced as an experimental version optimized for LiteRT deployment, designed to push the boundaries of on-device AI. Built to demonstrate the potential of running instruction-tuned models on mobile and edge devices, it represents ongoing efforts to make AI more accessible across hardware platforms.

+
+
+
+
Timeline
AnnouncedMay 20, 2025
ReleasedMay 20, 2025
Knowledge CutoffJun 1, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Gemma
Performance Overview
Performance metrics and category breakdown

Overall Performance

28 benchmarks
Average Score
43.9%
Best Score
78.9%
High Performers (80%+)
0
+
+
+
+
All Benchmark Results for Gemma 3n E2B Instructed LiteRT (Preview)
Complete list of benchmark scores with detailed information
PIQA
text
0.79
78.9%
Self-reported
BoolQ
text
0.76
76.4%
Self-reported
ARC-E
text
0.76
75.8%
Self-reported
HellaSwag
text
0.72
72.2%
Self-reported
Winogrande
text
0.67
66.8%
Self-reported
HumanEval
text
0.67
66.5%
Self-reported
TriviaQA
text
0.61
60.8%
Self-reported
MMLU
text
0.60
60.1%
Self-reported
Global-MMLU-Lite
text
0.59
59.0%
Self-reported
MBPP
text
0.57
56.6%
Self-reported
Showing 1 to 10 of 28 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+