Gemma 3n E4B Instruct
Gemma 3n E4B Instruct is a text-based AI model by Google. It features 51 tok/s output speed, $0.02/1M input tokens pricing. It scores 6.4 on the intelligence index.
Strengths
- +Very affordable pricing ($0.02/1M tokens)
Benchmarks
Intelligence6.4Coding4.2Math14.3
MMLU-Pro
0.5
GPQA
0.3
LiveCodeBench
0.1
Intelligence
6.4
Coding
4.2
Math
14.3
Output Speed
51 tok/s
Latency (TTFT)
0.32s
Blended Price
$0.03/M
Pricing per 1M Tokens
| Input (Prompt) | $0.02 |
| Output (Completion) | $0.04 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare Gemma 3n E4B Instruct with:
Alternatives to Gemma 3n E4B Instruct
More from Google
Frequently Asked Questions
How much does Gemma 3n E4B Instruct cost?
Gemma 3n E4B Instruct costs $0.02/1M input tokens and $0.04/1M output tokens.
Is Gemma 3n E4B Instruct good for coding?
Gemma 3n E4B Instruct has a lower coding score of 4.2. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is Gemma 3n E4B Instruct?
Gemma 3n E4B Instruct generates output at 51 tok/s. Time to first token is 0.32s.
Is there a free version of Gemma 3n E4B Instruct?
No, Gemma 3n E4B Instruct is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Gemma 3n E4B Instruct?
Last updated: