Hermes 2 models
4 Hermes 2 models on Hugging Face, from 6.7B to 46.7B parameters. At the precision each one is published in, the smallest needs about 15.1 GB of VRAM (Nous-Hermes-llama-2-7b, cheapest live fit: RTX 5060 Ti) and the largest about 104 GB (Nous-Hermes-2-Mixtral-8x7B-DPO, cheapest live fit: RTX 5060 Ti). The cheapest way to run Nous-Hermes-llama-2-7b is $0.110/hr.
Hermes 2 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Nous-Hermes-llama-2-7b | 6.7B | BF16 | 15.1 GB | RTX 5060 Ti | $0.110/hr |
| Nous-Hermes-2-Mistral-7B-DPO | 7.2B | BF16 | 16.2 GB | RTX A5000 | $0.176/hr |
| Hermes-2-Theta-Llama-3-8B | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| Nous-Hermes-2-Mixtral-8x7B-DPO | 46.7B | BF16 | 104 GB | RTX 5060 Ti × 7 | $0.770/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 3 (3 models)
