Loading…
Loading…
Models / EuroLLM
4 models (1.7B to 22B) · ↓ 424.3K downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Instructutter-project/EuroLLM-1.7B-Instruct | vLLM | 3.3 GB | 6.4 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| EuroLLM 9B Instruct 2512utter-project/EuroLLM-9B-Instruct-2512 | vLLM | 18 GB | 24.1 GB | $0.34/h 2x RTX 5060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| EuroLLM 22B Instruct 2512utter-project/EuroLLM-22B-Instruct-2512 | vLLM | 45 GB | 54.5 GB | $0.78/h 4x RTX 4060 Ti |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").