Gemma-3n-E4B and Llama-3.2-3B have no benchmarks in common in this dataset, so their scores cannot be compared directly. The specification and pricing rows below still apply.
Price basis: Standard rates vs listed rates. The price section below shows the applicable periods.
| Fact | Gemma-3n-E4B | Llama-3.2-3B |
|---|---|---|
| Context window | 32K tokens | 128K tokens |
| Input / 1M | Free | $0.150 |
| Output / 1M | Free | $0.150 |
| Blended (4:1) | Free | $0.150 |
| Status | Available | Available |
| Released | June 26, 2025 | September 18, 2024 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Published scores, with matching modes where available. Gaps show Gemma-3n-E4B relative to Llama-3.2-3B. Reading the results
A dash means no result is available.
| Benchmark | Gemma-3n-E4B | Llama-3.2-3B |
|---|---|---|
| GPQA Diamond | — | 26.6 |
| GSM8K | — | 34.0 |
| MATH | — | 8.5 |
| MMLU | — | 54.8 |
| MMLU-Pro | — | 25.0 |
| HumanEval | — | 28.0 |
| MBPP | — | 48.7 |
| Creative Writing | — | 594 |
| BALROG | — | 10.1 |
| BBH | — | 46.8 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Gemma-3n-E4B costs100%lessthan Llama-3.2-3B per million tokens.Using standard rates vs listed rates at this token mix.
Llama-3.2-3B: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Gemma-3n-E4B | Llama-3.2-3B | Ratio |
|---|---|---|---|
| Input | $0.00 | $0.15 | 0.00× |
| Output | $0.00 | $0.15 | 0.00× |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | $0.00 | $0.15 | 0.00× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
| Attribute | Gemma-3n-E4B | Llama-3.2-3B |
|---|---|---|
| Availability | Available | Available |
| Provider | Google Deep Mind | Facebook AI Research Lab |
| Model type | Foundation model | Foundation model |
| First release | June 26, 2025 | September 18, 2024 |
| Context window | 32K tokens | 128K tokens |
| Max output | 32K tokens | — |
| Total parameters | 4B | 3.2B |
| Architecture | Dense | Dense |
| Documented capabilities | Multilingual | — |
| Input modalities | Text, Image, Audio, Video | Text |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | Gemma Terms of Use | LLAMA 3.1 COMMUNITY LICENSE AGREEMENT |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Gemma-3n-E4B or Llama-3.2-3B? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.