Llama-3.2-3B and Gemma-3n-E4B 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: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Llama-3.2-3B | Gemma-3n-E4B |
|---|---|---|
| Context window | 128K tokens | 32K tokens |
| Input / 1M | $0.150 | Free |
| Output / 1M | $0.150 | Free |
| Blended (4:1) | $0.150 | Free |
| Status | Available | Available |
| Released | September 18, 2024 | June 26, 2025 |
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 Llama-3.2-3B relative to Gemma-3n-E4B. Reading the results
A dash means no result is available.
| Benchmark | Llama-3.2-3B | Gemma-3n-E4B |
|---|---|---|
| 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%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Llama-3.2-3B: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Llama-3.2-3B | Gemma-3n-E4B | Ratio |
|---|---|---|---|
| Input | $0.15 | $0.00 | — |
| Output | $0.15 | $0.00 | — |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | $0.15 | $0.00 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
| Attribute | Llama-3.2-3B | Gemma-3n-E4B |
|---|---|---|
| Availability | Available | Available |
| Provider | Facebook AI Research Lab | Google Deep Mind |
| Model type | Foundation model | Foundation model |
| First release | September 18, 2024 | June 26, 2025 |
| Context window | 128K tokens | 32K tokens |
| Max output | — | 32K tokens |
| Total parameters | 3.2B | 4B |
| Architecture | Dense | Dense |
| Documented capabilities | — | Multilingual |
| Input modalities | Text | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | LLAMA 3.1 COMMUNITY LICENSE AGREEMENT | Gemma Terms of Use |
| 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 Llama-3.2-3B or Gemma-3n-E4B? 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.