Hermes 3 models
3 Hermes 3 models on Hugging Face, from 8.0B to 405.9B parameters. At the precision each one is published in, the smallest needs about 17.9 GB of VRAM (Hermes-3-Llama-3.1-8B, cheapest live fit: RTX A5000) and the largest about 454 GB (Hermes-3-Llama-3.1-405B-FP8, cheapest live fit: RTX PRO 6000). The cheapest way to run Hermes-3-Llama-3.1-8B is $0.176/hr.
Hermes 3 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Hermes-3-Llama-3.1-8B | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| Hermes-3-Llama-3.1-70B | 70.6B | BF16 | 158 GB | RTX A5000 × 7 | $1.23/hr |
| Hermes-3-Llama-3.1-405B-FP8 | 405.9B | F8_E4M3 | 454 GB | RTX PRO 6000 × 5 | $6.88/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.
More from Nous Research
- Hermes 2 (4 models)
