Sarvam cloud models
3 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.
| Model | Intelligence | Speed (tok/s) |
|---|---|---|
| Sarvam 105B (High) | 8.8 | 213.579 |
| Sarvam 30B (High) | 6.6 | 0 |
| Sarvam M (Reasoning, Based on Mistral Small 3.1) | 5.3 | 0 |
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.