InternScience models
2 InternScience models on Hugging Face, from 4.5B to 35.1B parameters. At the precision each one is published in, the smallest needs about 10.1 GB of VRAM (Agents-A1-4B, cheapest live fit: RTX 3060) and the largest about 78.5 GB (Agents-A1, cheapest live fit: A100). The cheapest way to run Agents-A1-4B is $0.110/hr.
InternScience models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Agents-A1-4B | 4.5B | BF16 | 10.1 GB | RTX 3060 | $0.110/hr |
| Agents-A1 | 35.1B | BF16 | 78.5 GB | A100 | $1.31/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.
