Gemma 3n 2B
Gemma 3n 2B is Google's language model with a 8K context window and up to 2K output tokens. An instruction-tuned Gemma 3n model operating at an effective 2B parameter size, designed for multimodal instruction-following on-device.
Google's language model with a 8K context window and up to 2K output tokens. An instruction-tuned Gemma 3n model operating at an effective 2B parameter size, designed for multimodal instruction-following on-device.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Gemma 4 | — | — | — | — | Available |
| Gemma 4 26B A4B IT | — | — | — | — | Available |
| SEA-LION Gemma 4 27B IT | — | 8K | — | — | Available |
| Gemma 3n 2B | 8K | — | — | Current | |
| Gemma 3 12B IT | 131K | $0.040 | $0.100 | Available | |
| Gemma 3 4B Instruct | 128K | — | — | Available | |
| Gemma 3 4B IT | 131K | $0.040 | $0.080 | Available | |
| Gemma 3 | — | — | — | — | Available |
| Gemma 3 12B Instruct | — | 128K | $0.150 | $0.500 | Available |
| Gemma 3 1B Instruct | — | — | — | — | Available |
| Gemma 3 1B Instruct | — | — | — | — | Available |