Nous Research cloud models
7 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.
| Model | Intelligence | Speed (tok/s) |
|---|---|---|
| Hermes 4 - Llama-3.1 70B (Reasoning) | 10 | 95.686 |
| Hermes 4 - Llama-3.1 405B (Reasoning) | 9 | 40.724 |
| Hermes 4 - Llama-3.1 405B (Non-reasoning) | 8.8 | 40.494 |
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | 6.9 | 98.053 |
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | 5.3 | 0 |
| Hermes 3 - Llama-3.1 70B | 5.1 | 0 |
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | 2.3 | 0 |
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.