Nous Research models: prices and the hardware each needs
11 models, 1 sold per token by 1 vendor. Vendors are in alphabetical order; the price is the cheapest list price among them, per million tokens.
| Model | Size | Sold per token by | From, input | Output | GPU memory |
|---|---|---|---|---|---|
| Hermes 4 405B | 406 B | Nebius | $1.00 | $3.00 | 1014.6 GB |
| Hermes-2-Pro-Mistral-7B | 7.24 B | not sold per token | 18.1 GB | ||
| Hermes-3-Llama-3.1-8B | 8.03 B | not sold per token | 20.1 GB | ||
| Llama-3.2-1B (NousResearch) | 1.24 B | not sold per token | 3.1 GB | ||
| Meta-Llama-3-70B-Instruct (NousResearch) | 70.55 B | not sold per token | 176.4 GB | ||
| Meta-Llama-3-8B (NousResearch) | 8.03 B | not sold per token | 20.1 GB | ||
| Meta-Llama-3-8B-Instruct (NousResearch) | 8.03 B | not sold per token | 20.1 GB | ||
| Meta-Llama-3.1-8B (NousResearch) | 8.03 B | not sold per token | 20.1 GB | ||
| Meta-Llama-3.1-8B-Instruct (NousResearch) | 8.03 B | not sold per token | 20.1 GB | ||
| Nous-Hermes-2-Mixtral-8x7B-DPO | 46.7 B | not sold per token | 116.8 GB | ||
| Nous-Hermes-llama-2-7b | 6.74 B | not sold per token | 16.9 GB |