The AI arena is free today

Open Superagent

Gemma 3n E2B Instructed LiteRT (Preview) vs Gemma 3n E4B Instructed

Gemma 3n E4B Instructed leads the LLM Stats Score -5.1 to -10.1.

Google · Google · Updated for 2026

Which is better?

Gemma 3n E4B Instructed leads the overall LLM Stats Score -5.1 to -10.1, ranking #376 overall.

In the 17 individual benchmarks reported for both models, Gemma 3n E4B Instructed wins 16; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Gemma 3n E2B Instructed LiteRT (Preview)

  • you need open weights you can self-host or fine-tune

Choose Gemma 3n E4B Instructed

  • overall performance matters — it scores -5.1 and ranks #376 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 16 of 17 exact shared results
  • you want the most recent training data — it shipped Jun 2025

At a glance

The differences that matter most.

Gemma 3n E2B Instructed LiteRT (Preview)
Google
Gemma 3n E4B Instructed
Google
Core performance indexes
LLM Stats Score
-10.1
#391
-5.1
#376
Reasoning
-10.3
#384
-6.0
#375
Coding
-4.5
#281
-0.3
#266
Cost, coverage & limits
Benchmark wins
1 of 17
16 of 17
Input price
— / M
$20.00 / M
Output price
— / M
$40.00 / M
Context window
—
32,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Gemma 3n E2B Instructed LiteRT (Preview)
Gemma 3n E4B Instructed
Math
-6.4#335
-1.8#319
Finance
-9.6#235
-4.4#225
Legal
-9.6#216
-4.4#207
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

28 reported for Gemma 3n E2B Instructed LiteRT (Preview) · 18 for Gemma 3n E4B Instructed

17 shared

Gemma 3n E2B Instructed LiteRT (Preview) outperforms in 1 benchmarks (GPQA), while Gemma 3n E4B Instructed is better at 15 benchmarks (AIME 2025, Codegolf v2.2, ECLeKTic, Global-MMLU, Global-MMLU-Lite, HiddenMath, HumanEval, Include, LiveCodeBench v5, MBPP, MGSM, MMLU, MMLU-Pro, MMLU-ProX, WMT24++).

Gemma 3n E4B Instructed significantly outperforms across most benchmarks.

Mon Oct 26 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

6.1B diff

Gemma 3n E4B Instructed has 6.1B more parameters than Gemma 3n E2B Instructed LiteRT (Preview), making it 318.8% larger.

Google
Gemma 3n E2B Instructed LiteRT (Preview)
1.9Bparameters
Google
Gemma 3n E4B Instructed
8.0Bparameters
1.9B
Gemma 3n E2B Instructed LiteRT (Preview)
8.0B
Gemma 3n E4B Instructed

Context Window

Maximum input and output token capacity

Only Gemma 3n E4B Instructed specifies input context (32,000 tokens). Only Gemma 3n E4B Instructed specifies output context (32,000 tokens).

Google
Gemma 3n E2B Instructed LiteRT (Preview)
Input- tokens
Output- tokens
Google
Gemma 3n E4B Instructed
Input32,000 tokens
Output32,000 tokens
Mon Oct 26 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Gemma 3n E2B Instructed LiteRT (Preview) and Gemma 3n E4B Instructed support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Gemma 3n E2B Instructed LiteRT (Preview)

Text
Images
Audio
Video

Gemma 3n E4B Instructed

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3n E2B Instructed LiteRT (Preview) is licensed under Gemma, while Gemma 3n E4B Instructed uses a proprietary license.

License differences may affect how you can use these models in commercial or open-source projects.

Gemma 3n E2B Instructed LiteRT (Preview)

Gemma

Open weights

Gemma 3n E4B Instructed

Proprietary

Closed source

Release Timeline

When each model was launched

Gemma 3n E2B Instructed LiteRT (Preview) was released on 2025-05-20, while Gemma 3n E4B Instructed was released on 2025-06-26.

Gemma 3n E4B Instructed is 1 month newer than Gemma 3n E2B Instructed LiteRT (Preview).

Gemma 3n E2B Instructed LiteRT (Preview)

May 20, 2025

1.4 years ago

Gemma 3n E4B Instructed

Jun 26, 2025

1.3 years ago

1mo newer

Knowledge Cutoff

When training data ends

Both models have the same knowledge cutoff date of 2024-06-01.

They should have similar awareness of historical events and information up to this date.

Gemma 3n E2B Instructed LiteRT (Preview)

Jun 2024

Gemma 3n E4B Instructed

Jun 2024

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Gemma 3n E2B Instructed LiteRT (Preview) and Gemma 3n E4B Instructed side-by-side, then vote on the output you prefer.

Gemma 3n E2B Instructed LiteRT (Preview)
✓ Preferred
Gemma 3n E4B Instructed
Open in Playground

FAQ

Common questions about Gemma 3n E2B Instructed LiteRT (Preview) vs Gemma 3n E4B Instructed.

Which is better, Gemma 3n E2B Instructed LiteRT (Preview) or Gemma 3n E4B Instructed?

Gemma 3n E4B Instructed leads the LLM Stats Score -5.1 to -10.1. Gemma 3n E2B Instructed LiteRT (Preview) is made by Google and Gemma 3n E4B Instructed is made by Google. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Gemma 3n E2B Instructed LiteRT (Preview) compare to Gemma 3n E4B Instructed in benchmarks?

Gemma 3n E2B Instructed LiteRT (Preview) scores PIQA: 78.9%, BoolQ: 76.4%, ARC-E: 75.8%, HellaSwag: 72.2%, Winogrande: 66.8%. Gemma 3n E4B Instructed scores HumanEval: 75.0%, MGSM: 67.0%, MMLU: 64.9%, Global-MMLU-Lite: 64.5%, MBPP: 63.6%.

What are the context window sizes for Gemma 3n E2B Instructed LiteRT (Preview) and Gemma 3n E4B Instructed?

Gemma 3n E2B Instructed LiteRT (Preview) supports an unknown number of tokens and Gemma 3n E4B Instructed supports 32K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemma 3n E2B Instructed LiteRT (Preview) and Gemma 3n E4B Instructed?

Key differences include LLM Stats Score (-10.1 vs -5.1), licensing (Gemma vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Related comparisons