Allen Institute for AI cloud models
10 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.
| Model | Intelligence | Speed (tok/s) |
|---|---|---|
| Llama 3.1 Tulu3 405B | 8.3 | 0 |
| Olmo 3.1 32B Think | 8.1 | 0 |
| Olmo 3.1 32B Instruct | 6.5 | 0 |
| Olmo 3 32B Think | 6.4 | 0 |
| OLMo 2 32B | 5 | 0 |
| Olmo 3 7B Think | 4 | 0 |
| OLMo 2 7B | 3.9 | 0 |
| Molmo 7B-D | 3.8 | 0 |
| Olmo 3 7B Instruct | 2.8 | 0 |
| Molmo2-8B | 2 | 0 |
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.