Code Llama
Meta's open-source code LLM
Category
LLM Providers for Code
Platforms
api, cli
Pricing
$0 — $0
Open Source
Yes
IDE Support
Ollama, Any via API
What is Code Llama?
Code Llama is Meta's family of open-source LLMs specifically trained for code generation. Available in 7B, 13B, 34B, and 70B parameter sizes. Can be run locally via Ollama.
Who is it for? Developers building AI-powered applications who need reliable model APIs.
Key Features
Available on
Our Verdict
The go-to open-source code model for local/private use. 70B variant is quite capable.
Pros & Cons
Pros
- + Fully open source
- + Run locally for privacy
- + Multiple sizes available
- + Good code quality
Cons
- - Requires GPU for best models
- - Quality below commercial models
- - No official cloud API
- - Training data cutoff
Pricing
Open Source
$0
- Full model weights
- Run locally
- Commercial use
Supported Languages & IDEs
Compare Code Llama
Alternatives to Code Llama
Claude (Anthropic)
The most capable AI for complex coding
Free 4.8/5
OpenAI GPT-4
The most popular AI for coding
Free 4.6/5
Mistral AI
European AI company with best-in-class open models
Free OSS 4.4/5
DeepSeek Coder
Open-source code LLM
Free OSS 4.3/5
Google Gemini
Google's multimodal AI for coding
Free 4.3/5
Qwen2.5-Coder
Alibaba's open-source code-specialized LLM
Free OSS 4.2/5
About Meta
Company Meta
Founded 2023
HQ Menlo Park, CA
Repository
github.com/meta-llama/codellama — 16.0k stars
Status Active
Data updated 2025-01-15