Gemma 3n models
4 Gemma 3n models on Hugging Face, from 5.4B to 8.4B parameters. At the precision each one is published in, the smallest needs about 12.2 GB of VRAM (gemma-3n-E2B-it, cheapest live fit: RTX 5060 Ti) and the largest about 18.7 GB (gemma-3n-E4B-it, cheapest live fit: RTX A5000). The cheapest way to run gemma-3n-E2B-it is $0.110/hr.
Gemma 3n models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gemma-3n-E2B-it | 5.4B | BF16 | 12.2 GB | RTX 5060 Ti | $0.110/hr |
| gemma-3n-E4B-it | 7.8B | BF16 | 17.5 GB | RTX A5000 | $0.176/hr |
| gemma-3n-E4B-it-MLX-bf16 | 7.8B | BF16 | 17.5 GB | RTX A5000 | $0.176/hr |
| gemma-3n-E4B-it | 8.4B | BF16 | 18.7 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
