ModelAI for Codevcodellama-34b-instruct

Code Llama 34B

by Meta · free · Last verified 2026-03-17

Code Llama 34B is a large language model from Meta, fine-tuned from Llama 2 for code-specific tasks. It excels at generating, completing, and explaining code across various languages. With variants supporting a 100K token context window, it can analyze and work with extensive codebases for complex tasks like refactoring.

https://ai.meta.com/blog/code-llama-large-language-model-coding/ ↗

B—Above Average

Adoption: B+Quality: B+Freshness: BCitations: B+Engagement: F

Specifications

License: Llama 2 Community License
Pricing: free
Capabilities: Code generation from natural language, Code completion and autocompletion, Code infilling for filling gaps in code, Instruction-based code editing and refactoring, Code explanation and summarization, Debugging assistance, Long-context code analysis (up to 100K tokens), Multi-language programming support
Integrations
Use Cases: [object Object], [object Object], [object Object], [object Object], [object Object]
API Available: Yes
Parameters: 34B
Context Window: 16K tokens (100K extended)
Modalities: text
Training Cutoff: Mid 2023
Tags: code-llm, open-source, code-generation, infilling, instruction-tuned, meta-ai, large-language-model, developer-tools, code-analysis, long-context
Added: 2026-03-17
Completeness: 0.9%

Index Score

64.3

Adoption

Quality

Freshness

Citations

Engagement

Need help choosing the right model?

Get Expert Guidance

Explore the full AI ecosystem on Agents as a Service