Google model product
Gemma 3n E2B LiteRT
Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets.
Updated Aug 12, 2026. Default version: Gemma 3n E2B Instructed LiteRT (Preview)
LLMBoard score0.0Gemma 3n E2B Instructed LiteRT (Preview)
Coverage100%28 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Gemma 3n E2B LiteRT Specifications
Technical details for the model's default version.
- Version
- Gemma 3n E2B Instructed LiteRT (Preview)
- Released
- May 20, 2025
- Knowledge cutoff
- Jun 1, 2024
- Parameters
- 1.9B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Gemma
Gemma 3n E2B LiteRT Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 3n E2B LiteRT Benchmark Results
Benchmark scores for Gemma 3n E2B Instructed LiteRT (Preview).
| Codegolf v2.2 | 11.0% | 04 | 4 | 0.0% | C | |
| Global-MMLU | 55.1% | 05 | 5 | 0.0% | C | |
| ECLeKTic | 2.5% | 06 | 8 | 28.6% | C | |
| ARC-E | 75.8% | 07 | 8 | 14.3% | C | |
| Natural Questions | 15.5% | 07 | 7 | 0.0% | C | |
| LiveCodeBench v5 | 18.6% | 09 | 9 | 0.0% | C | |
| PIQA | 78.9% | 09 | 11 | 20.0% | C | |
| Social IQa | 48.8% | 09 | 9 | 0.0% | C | |
| BoolQ | 76.4% | 10 | 10 | 0.0% | C | |
| Global-MMLU-Lite | 59.0% | 12 | 14 | 15.4% | C | |
| HiddenMath | 27.7% | 12 | 13 | 8.3% | C | |
| TriviaQA | 60.8% | 17 | 18 | 5.9% | C | |
| BIG-Bench Hard | 44.3% | 20 | 21 | 5.0% | C | |
| Winogrande | 66.8% | 21 | 22 | 4.8% | C | |
| WMT24++ | 42.7% | 21 | 23 | 9.1% | C | |
| HellaSwag | 72.2% | 23 | 27 | 15.4% | C | |
| DROP | 53.9% | 27 | 30 | 10.3% | C | |
| MGSM | 53.1% | 30 | 31 | 3.3% | C | |
| Include | 38.6% | 31 | 31 | 0.0% | C | |
| MBPP | 56.6% | 31 | 33 | 6.3% | C | |
| ARC-C | 51.7% | 32 | 34 | 6.1% | C | |
| MMLU-ProX | 8.1% | 32 | 32 | 0.0% | C | |
| HumanEval | 66.5% | 61 | 66 | 7.7% | C | |
| LiveCodeBench | 13.2% | 69 | 73 | 5.6% | C | |
| MMLU | 60.1% | 99 | 100 | 1.0% | C | |
| AIME 2025 | 6.7% | 114 | 114 | 0.0% | C | |
| MMLU-Pro | 40.5% | 126 | 129 | 2.3% | C | |
| GPQA | 24.8% | 230 | 234 | 1.7% | C |
Gemma 3n E2B LiteRT Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Gemma 3n E2B LiteRT Runtime Performance
Provider-specific output speed and catalog latency for Gemma 3n E2B Instructed LiteRT (Preview). Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemma 3n E2B LiteRT Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemma 3n E2B LiteRT Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemma 3n E2B Instructed LiteRT (Preview) | 0.0 | 1.9B | N/A | N/A | No | Gemma |
What is Gemma 3n E2B LiteRT?
Key information about Gemma 3n E2B LiteRT and its available data.
Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets. It features innovations like Per-Layer Embedding (PLE) parameter caching and a MatFormer model architecture for reduced compute and memory.
These models handle audio, text, and visual data, though this E4B preview currently supports text and vision input. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models, and is licensed for responsible commercial use.
Data as of 2026-08-11.
Gemma 3n E2B LiteRT vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemma 3n E2B LiteRT
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemma 3n E2B
GOGoogle
Gemini 1.5 Flash 8B
GOGoogle
Gemma 3n E4B
GOGoogle
MedGemma 4B IT
GOGoogle
Gemma 3n E4B LiteRT
GOGoogle
Gemma 3 4B
FAQ
Common questions about Gemma 3n E2B LiteRT.
When was Gemma 3n E2B LiteRT released?
Gemma 3n E2B LiteRT's default version was released on May 20, 2025.
How much does Gemma 3n E2B LiteRT cost?
No official standard PAYG price is currently available for Gemma 3n E2B LiteRT.
Who created Gemma 3n E2B LiteRT?
Gemma 3n E2B LiteRT was created by Google.
What is the context window for Gemma 3n E2B LiteRT?
A context window is not available for the default version.
Is Gemma 3n E2B LiteRT open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemma 3n E2B LiteRT?
No provider offering is currently linked to the default version.
What models should I compare Gemma 3n E2B LiteRT with?
Nearby ranked alternatives include Pixtral 12B, Gemma 3n E4B, GPT-5.1-Codex-Mini.