EuroLLM models
3 EuroLLM models on Hugging Face, from 1.7B to 9.2B parameters. At the precision each one is published in, the smallest needs about 3.7 GB of VRAM (EuroLLM-1.7B-Instruct, cheapest live fit: RTX 5060 Ti) and the largest about 20.5 GB (EuroLLM-9B-Instruct, cheapest live fit: RTX A5000). The cheapest way to run EuroLLM-1.7B-Instruct is $0.110/hr.
EuroLLM models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| EuroLLM-1.7B-Instruct | 1.7B | BF16 | 3.7 GB | RTX 5060 Ti | $0.110/hr |
| EuroLLM-9B-Instruct | 9.2B | BF16 | 20.5 GB | RTX A5000 | $0.176/hr |
| EuroLLM-9B-Instruct-2512 | 9.2B | BF16 | 20.5 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.
