Code Llama

Code Llama is a 2023-era family of code-specialized large language models (LLMs) Meta built on Llama 2 for generating, completing, and explaining source code. Meta archived the Code Llama repository in 2025, and the models are no longer actively maintained. Meta’s coding capabilities now come from its general-purpose Llama 3.x and Llama 4 models, plus the coding-optimized Muse Spark models and the Muse Code terminal agent.

The 7B and 13B variants support infilling completions in the middle of code or text, and all the models can handle long input contexts for code generation. They’re distributed as model weights for local or cloud inference and are widely accessible through common libraries and the Hugging Face ecosystem.

Official website: Meta AI

Related Resources

Tutorial

How to Use Ollama to Run Large Language Models Locally

Learn how to use Ollama to run large language models locally. Install it, pull models, and start chatting from your terminal without needing API keys.

intermediate ai tools

For additional information on related topics, take a look at the following resources:

• Hugging Face Transformers: Leverage Open-Source AI in Python (Tutorial)
• How to Use Ollama to Run Large Language Models Locally (Quiz)
• Hugging Face Transformers (Quiz)