Model Library
GoogleReleased April 3, 2026Gemma 4 E4B
Google · Released April 3, 2026
Intelligence score
9
At a glance
- Intelligence
- 9
- Speed
- —
- Latency
- —
- Input price
- Not published
- Output price
- Not published
- Context window
- 130Ktokens
- Parameters
- 8billions
Summary
Comparison summary
Gemma 4 E4B (Non-reasoning) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
Specifications
Technical specifications
| Model name | Gemma 4 E4B |
|---|---|
| Provider | |
| Release date | April 3, 2026 |
| Intelligence score | 9 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | Not published |
| Output price | Not published |
| Context window | 130,000 tokens |
| Parameters | 8B |
| Reasoning | No |
| Input modalities | text, image, audio, video |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: gemma-4-e4b-non-reasoning |
FAQ · 16
Frequently asked questions
Gemma 4 E4B (Non-reasoning) was released on April 3, 2026.
Gemma 4 E4B (Non-reasoning) was created by Google.
Gemma 4 E4B (Non-reasoning) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
No, Gemma 4 E4B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Gemma 4 E4B (Non-reasoning) supports text, image, speech, and video input.
Gemma 4 E4B (Non-reasoning) supports text output.
Yes, Gemma 4 E4B (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Gemma 4 E4B (Non-reasoning) is multimodal. It can process text, image, speech, and video input and generate text output.
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.
Yes, Gemma 4 E4B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Gemma 4 E4B (Non-reasoning) has 8 billion parameters (4.5 billion active).
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.
Gemma 4 E4B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Gemma 4 E4B (Non-reasoning) achieves a score of 9 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Gemma 4 E4B (Non-reasoning) is an open weights model that can be self-hosted.
Gemma 4 E4B (Non-reasoning) is an open weights model that can be downloaded and self-hosted.