---
license: apache-2.0
base_model:
- sarvamai/sarvam-m
---

# Sarvam-M
<p align="center">
  <a href="https://dashboard.sarvam.ai/playground"
     target="_blank" rel="noopener noreferrer">
    <img
      src="https://img.shields.io/badge/🚀 Chat on Sarvam&nbsp;Playground-1488CC?style=for-the-badge&logo=rocket"
      alt="Chat on Sarvam Playground"
    />
  </a>
</p>

# Model Information

> [!Note]
> This repository contains gguf version of [`sarvam-m`](https://huggingface.co/sarvamai/sarvam-m) in q8 precision.

Learn more about sarvam-m in our detailed [blog post](https://www.sarvam.ai/blogs/sarvam-m).

# Running the model on a CPU

You can use the model on your local machine (without gpu) as explained [here](https://github.com/ggml-org/llama.cpp/tree/master/tools/main).

Example Command:
```
./build/bin/llama-cli -i -m /your/folder/path/sarvam-m-q8_0.gguf -c 8192 -t 16
```