β All modelsMODEL FAMILY
Gemma 4 β every size compared
Google's Gemma 4 family spans 5 models from 5.1B to 30.7B parameters. The smallest needs just 6 GB of RAM; the largest wants 32 GB.
All Gemma 4 models
| Model | Params | Download (Q4) | Min RAM | Context window | Best for |
|---|---|---|---|---|---|
| Gemma 4 E2B | 5.1B (A2.3B) | 3.1 GB | 6 GB | 128K | Chat, Vision |
| Gemma 4 E4B | 8B (A4.5B) | 4.9 GB | 8 GB | 128K | Chat, Vision |
| Gemma 4 12B | 12B | 7.3 GB | 12 GB | 256K | Chat, Coding, Reasoning, Vision |
| Gemma 4 26B A4B | 25.2B (A3.8B) | 15.3 GB | 24 GB | 256K | Chat, Coding, Reasoning, Vision |
| Gemma 4 31B | 30.7B | 18.6 GB | 32 GB | 256K | Chat, Coding, Reasoning, 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 4 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.