Gemma models
3 Gemma models on Hugging Face, from 2.5B to 8.5B parameters. At the precision each one is published in, the smallest needs about 5.6 GB of VRAM (gemma-1.1-2b-it, cheapest live fit: RTX 5060 Ti) and the largest about 19.1 GB (gemma-7b, cheapest live fit: RTX A5000). The cheapest way to run gemma-1.1-2b-it is $0.110/hr.
Gemma models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gemma-1.1-2b-it | 2.5B | BF16 | 5.6 GB | RTX 5060 Ti | $0.110/hr |
| gemma-7b | 8.5B | BF16 | 19.1 GB | RTX A5000 | $0.176/hr |
| gemma-7b-it | 8.5B | BF16 | 19.1 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.
