Meta cloud models
22 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.
| Model | Intelligence | Speed (tok/s) |
|---|---|---|
| Muse Spark 1.3 (max) | 53 | 176.544 |
| Muse Spark 1.3 (xhigh) | 51.6 | 107.866 |
| Muse Spark 1.2 (xhigh) | 46.8 | 223.575 |
| Muse Spark 1.1 (xhigh) | 43.3 | 0 |
| Muse Spark | 35.8 | 0 |
| Muse Glimmer (high) | 24.4 | 95.494 |
| Llama 4 Maverick | 8.5 | 84.533 |
| Llama 4 Scout | 4.6 | 85.219 |
| Llama 3.3 Instruct 70B | 3.7 | 90.363 |
| Llama 3.1 Instruct 405B | 2.9 | 0 |
| Llama 3.1 Instruct 8B | 2 | 0 |
| Llama 3.1 Instruct 70B | 1.2 | 0 |
| Llama 3.2 Instruct 90B (Vision) | 1 | 0 |
| Llama 3.2 Instruct 11B (Vision) | 1 | 26.83 |
| Llama 65B | 1 | 0 |
| Llama 3.2 Instruct 3B | 1 | 0 |
| Llama 3 Instruct 70B | 1 | 0 |
| Llama 3 Instruct 8B | 1 | 0 |
| Llama 3.2 Instruct 1B | 1 | 0 |
| Llama 2 Chat 70B | 1 | 0 |
| Llama 2 Chat 13B | 1 | 0 |
| Llama 2 Chat 7B | 1 | 0 |
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.