Model comparison
Gemma 3n vs Gemma 3
- Input
- $0.06 / 1M tokens
- Output
- $0.12 / 1M tokens
- Context
- 32K
- Released
- 2025-06-26
- Input
- $0.08
- Output
- $0.16
- Context
- 128K
- Released
- 2025-03-12
Gemma 3 scores higher on 1 of the 1 benchmarks both models report; Gemma 3n is cheaper on input tokens ($0.1 vs $0.1 per 1M, 1.3×); Gemma 3 has the larger context window (128K vs 32K).
Specs and pricing side by side
| Spec | Gemma 3n | Gemma 3 |
|---|---|---|
| Maker | Googlesame | |
| Released | 2025-06-26 | 2025-03-12 |
| Context window | 32K | 128K |
| Max output | 32K tokens (shared with input) | 8K |
| Input price | $0.06 / 1M tokens | $0.08 |
| Output price | $0.12 / 1M tokens | $0.16 |
| Parameters | E2B: 5B raw / ~2B effective; E4B: 8B raw / ~4B effective | 1B · 4B · 12B · 27B (270M added Aug 2025) |
| License | Gemma Terms of Use (open weights, commercial use permitted) | Gemma Terms of Use |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision, Audio, Video | Text, Vision |
| Knowledge cutoff | June 2024 | August 2024 |
Benchmarks both models report
| Benchmark | Gemma 3n | Gemma 3 |
|---|---|---|
| HumanEval | 75% | 87.8% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Gemma 3n if…
- Cost matters: input tokens cost 1.3× less ($0.1 vs $0.1 per 1M).
- You need Audio / Video input, which Gemma 3 lacks.
- Your use case is: on-device assistants and chat apps that work offline.
Pick Gemma 3 if…
- You care about HumanEval (it scores higher on 1 shared benchmark).
- You need the longer context (128K vs 32K).
- Your use case is: self-hosted chat and assistants where data must stay local.
FAQ
Which is better, Gemma 3n or Gemma 3?
Gemma 3 scores higher on 1 of the 1 benchmarks both models report; Gemma 3n is cheaper on input tokens ($0.1 vs $0.1 per 1M, 1.3×); Gemma 3 has the larger context window (128K vs 32K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Gemma 3n?
Gemma 3n: $0.06 / 1M tokens input, $0.12 / 1M tokens output. Gemma 3: $0.08 input, $0.16 output (list API prices as published by each maker).
What are the context windows of Gemma 3n and Gemma 3?
Gemma 3n offers 32K with up to 32K tokens (shared with input) output; Gemma 3 offers 128K with up to 8K output.
Is Gemma 3n newer than Gemma 3?
Gemma 3n was released 2025-06-26; Gemma 3 was released 2025-03-12.