Gemma 4 E4B (Non-reasoning)
Intelligence
14.8
#341/521
Coding
6.4
#372/427
Math
—
Speed
—
Pricing
—
Gemma 4 E4B (Non-reasoning) is Google’s model designed for various applications in data processing. It operates at a speed of 0 tokens per second and is priced at $0 per million tokens, making it accessible for users requiring cost-effective solutions.
When to Use Gemma 4 E4B (Non-reasoning)
✓ Best For
- Data processing tasks
- Basic coding assistance
- Applications requiring non-reasoning capabilities
✗ Not Ideal For
- High-speed processing needs
- Complex reasoning tasks
How Gemma 4 E4B (Non-reasoning) Compares
Intelligence Index · Higher is better
UpstageNVIDIAGoogleMistral
Benchmark Profile
Coding Index
MetaAnthropicGoogleTrillion Labs
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 14.8 | |
| Coding Index | 6.4 | |
| GPQA | 549% | |
| HLE | 47% | |
| SciCode | 3.9% | |
| IFBench | 40.5% | |
| LCR | 18% | |
| TerminalBench Hard | 7.6% | |
| Tau2 | 26% |
Data: Artificial Analysis · Updated: April 7, 2026
Frequently Asked Questions (15)
When was Gemma 4 E4B (Non-reasoning) released?
Gemma 4 E4B (Non-reasoning) was released on April 3, 2026.
Who created Gemma 4 E4B (Non-reasoning)?
Gemma 4 E4B (Non-reasoning) was created by Google.
How intelligent is Gemma 4 E4B (Non-reasoning)?
Gemma 4 E4B (Non-reasoning) scores 15 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 11).
How verbose is Gemma 4 E4B (Non-reasoning)?
When evaluated on the Intelligence Index, Gemma 4 E4B (Non-reasoning) generated 7.9M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 4.7M).
Is Gemma 4 E4B (Non-reasoning) a reasoning model?
No, Gemma 4 E4B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Gemma 4 E4B (Non-reasoning) support?
Gemma 4 E4B (Non-reasoning) supports text, image, speech, and video input.
What output modalities does Gemma 4 E4B (Non-reasoning) support?
Gemma 4 E4B (Non-reasoning) supports text output.
Can Gemma 4 E4B (Non-reasoning) process images?
Yes, Gemma 4 E4B (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Gemma 4 E4B (Non-reasoning) multimodal?
Yes, Gemma 4 E4B (Non-reasoning) is multimodal. It can process text, image, speech, and video input and generate text output.
What is the context window of Gemma 4 E4B (Non-reasoning)?
Gemma 4 E4B (Non-reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Gemma 4 E4B (Non-reasoning) open source?
Yes, Gemma 4 E4B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Gemma 4 E4B (Non-reasoning) have?
Gemma 4 E4B (Non-reasoning) has 8 billion parameters (4.5 billion active).
What are the active parameters of Gemma 4 E4B (Non-reasoning)?
Gemma 4 E4B (Non-reasoning) is a Mixture of Experts (MoE) model with 8 billion total parameters, but only 4.5 billion active parameters are used during inference.
What is the license for Gemma 4 E4B (Non-reasoning)?
Gemma 4 E4B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.
How does Gemma 4 E4B (Non-reasoning) perform on benchmarks?
Gemma 4 E4B (Non-reasoning) achieves a score of 15 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
