β All modelsMODEL FAMILY
Gemma 3 β every size compared
Google's Gemma 3 family spans 5 models from 1B to 27.4B parameters. The smallest needs just 3 GB of RAM; the largest wants 24 GB.
All Gemma 3 models
| Model | Params | Download (Q4) | Min RAM | Context window | Best for |
|---|---|---|---|---|---|
| Gemma 3 1B | 1B | 0.6 GB | 3 GB | 32K | Chat |
| Gemma 3 4B | 4.3B | 2.6 GB | 6 GB | 128K | Chat, Vision |
| Gemma 3n E4B | 7.8B (A4B) | 4.7 GB | 8 GB | 32K | Chat, Vision |
| Gemma 3 12B | 12.2B | 7.4 GB | 12 GB | 128K | Chat, Vision |
| Gemma 3 27B | 27.4B | 16.6 GB | 24 GB | 128K | Chat, Vision |
Sizes are 4-bit (Q4_K_M) GGUF builds β the standard for running models locally. Β· Data updated: 2026-06-11 Β· How we calculate these numbers β
Which Gemma 3 should you pick?
Take the largest one your memory allows β bigger versions of the same family are almost always better at the same quantization. Click any model for full requirements and a live check on your machine.