Loading…
Loading…
Models / Hermes-3-Llama-3.1
3 models (8B to 405B) · ↓ 598K downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalNousResearch/Hermes-3-Llama-3.1-8B | vLLM | 16 GB | 21.3 GB | $0.18/h 2x RTX 3060 |
| AWQ (solidrust)solidrust/Hermes-3-Llama-3.1-8B-AWQ | vLLM | 5.7 GB | 9.8 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalNousResearch/Hermes-3-Llama-3.1-70B | vLLM | 141 GB | 162 GB | $1.38/h 8x RTX 3090 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalNousResearch/Hermes-3-Llama-3.1-405B | vLLM | 812 GB | 908.8 GB | $44.03/h 8x Nvidia H200 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").