Grok 2 (Quantized GGUF)

Powered by xAI

Model Details

• Original Model: grok-2
• Created by: xAI
• Release year: 2024

This is a quantized version of the Grok 2 model, provided in GGUF format for compatibility with llama.cpp and Ollama.

Sources

• Original Model Repository (xAI): https://huggingface.co/xai-org/grok-2
  
• Quantized GGUF by Unsloth: https://huggingface.co/unsloth/grok-2-GGUF
  

Packaging

The quantized GGUF weights were merged from the sharded release provided by Unsloth using the official llama.cpp utilities:

llama-gguf-split --merge

Resulting in a single GGUF file suitable for use with Ollama.

Usage

After installing Ollama, you can run the model locally with:

ollama run MichelRosselli/grok-2

License

The weights are licensed under the Grok 2 Community License Agreement.

This product includes materials licensed under the xAI Community License. Copyright © 2025 xAI. All rights reserved.