allenai models
2 allenai models on Hugging Face, from 7.2B to 7.4B parameters. At the precision each one is published in, the smallest needs about 16.2 GB of VRAM (wildguard, cheapest live fit: RTX A5000) and the largest about 16.6 GB (Olmo-Hybrid-7B, cheapest live fit: RTX A5000). The cheapest way to run wildguard is $0.176/hr.
allenai models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| wildguard | 7.2B | BF16 | 16.2 GB | RTX A5000 | $0.176/hr |
| Olmo-Hybrid-7B | 7.4B | BF16 | 16.6 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.
