Model Library
GoogleReleased June 26, 2025Gemma 3n E4B
Google · Released June 26, 2025
Intelligence score
1
At a glance
- Intelligence
- 1
- Speed
- 55.7tokens/sec
- Latency
- 1.30stime to first token
- Input price
- $0.02per 1M tokens
- Output price
- $0.04per 1M tokens
- Context window
- 32Ktokens
- Parameters
- 8.39billions
Summary
Comparison summary
Gemma 3n E4B Instruct scores 1 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6). Gemma 3n E4B Instruct generates output at 55.7 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 102.7 t/s). Gemma 3n E4B Instruct costs $0.02 per 1M input tokens (very competitive, median: $0.15) and $0.04 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Gemma 3n E4B |
|---|---|
| Provider | |
| Release date | June 26, 2025 |
| Intelligence score | 1 |
| Speed | 55.7 tokens/sec |
| Latency (TTFT) | 1.30s |
| Input price | $0.02 / 1M tokens |
| Output price | $0.04 / 1M tokens |
| Context window | 32,000 tokens |
| Parameters | 8.39B |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Gemma license |
| API availability | — |
| Source | Model Intelligence legacy profile: gemma-3n-e4b |
Pricing
Token prices
Price per 1M tokens
Gemma 3n E4B, as listed in the catalog record
- Input$0.02
- Output$0.04
| Token type | Price per 1M |
|---|---|
| Input | $0.02 |
| Output | $0.04 |
Model Intelligence legacy profile: gemma-3n-e4b
FAQ · 21
Frequently asked questions
Gemma 3n E4B Instruct was released on June 26, 2025.
Gemma 3n E4B Instruct was created by Google.
Gemma 3n E4B Instruct scores 1 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6).
Gemma 3n E4B Instruct generates output at 55.7 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 102.7 t/s).
Gemma 3n E4B Instruct has a time to first token (TTFT) of 1.30s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
Gemma 3n E4B Instruct costs $0.02 per 1M input tokens (very competitive, median: $0.15) and $0.04 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.
Gemma 3n E4B Instruct costs $0.02 per 1M input tokens and $0.04 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.02 per 1M tokens. Pricing may vary by provider.
No, Gemma 3n E4B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Gemma 3n E4B Instruct supports text and image input.
Gemma 3n E4B Instruct supports text output.
Yes, Gemma 3n E4B Instruct supports image input and can analyze, describe, and answer questions about images.
Yes, Gemma 3n E4B Instruct is multimodal. It can process text and image input and generate text output.
Gemma 3n E4B Instruct has a context window of 32k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Gemma 3n E4B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Gemma 3n E4B Instruct has 8.39 billion parameters (4 billion active).
Gemma 3n E4B Instruct is a Mixture of Experts (MoE) model with 8.39 billion total parameters, but only 4 billion active parameters are used during inference.
Gemma 3n E4B Instruct is released under the Gemma license license. This license allows commercial use.
Gemma 3n E4B Instruct achieves a score of 1 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Gemma 3n E4B Instruct has a knowledge cutoff of August 2024. The model's training data includes information up to this date.
Yes, Gemma 3n E4B Instruct is available via API through 1 provider.
Gemma 3n E4B Instruct is available through 1 API provider.