Gemma 2 models
16 Gemma 2 models on Hugging Face, from 2.5B to 27.2B parameters. At the precision each one is published in, the smallest needs about 5.6 GB of VRAM (gemma-2b, cheapest live fit: RTX 5060 Ti) and the largest about 122 GB (gemma-2-27b, cheapest live fit: V100). The cheapest way to run gemma-2b is $0.110/hr.
Gemma 2 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gemma-2b | 2.5B | BF16 | 5.6 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2b-it | 2.5B | BF16 | 5.6 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2b-it | 2.5B | BF16 | 5.6 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2-2b-it | 2.6B | BF16 | 5.8 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2-2b | 2.6B | F32 | 11.7 GB | V100 | $0.088/hr |
| gemma-2-2b-it | 2.6B | BF16 | 5.8 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2-2b | 2.6B | BF16 | 5.8 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2-2b-it | 2.6B | BF16 | 5.8 GB | RTX 5060 Ti | $0.110/hr |
| gemma-2-9b | 9.2B | F32 | 41.3 GB | RTX A6000 | $0.363/hr |
| gemma-2-9b-it | 9.2B | BF16 | 20.7 GB | RTX A5000 | $0.176/hr |
| gemma-2-9b-it | 9.2B | BF16 | 20.7 GB | RTX A5000 | $0.176/hr |
| gemma-2-9b | 9.2B | BF16 | 20.7 GB | RTX A5000 | $0.176/hr |
| gemma-2-9b-it | 9.2B | BF16 | 20.7 GB | RTX A5000 | $0.176/hr |
| gemma-2-27b | 27.2B | F32 | 122 GB | V100 × 8 | $0.704/hr |
| gemma-2-27b-it | 27.2B | BF16 | 60.9 GB | A100 | $1.21/hr |
| gemma-2-27b | 27.2B | BF16 | 60.9 GB | A100 | $1.21/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.
