Code Llama 34B
Meta's specialized code generation model
Code Llama 34B
Meta • August 2023
Training Data
Up to early 2023
Code Llama 34B
August 2023
Parameters
34 billion
Training Method
Code-specialized training
Context Window
16,384 tokens
Knowledge Cutoff
January 2023
Key Features
Code Specialization • Open Source • Fill-in-the-middle
Capabilities
Coding: Outstanding
Code Completion: Excellent
Debugging: Very Good
What's New in This Version
Specialized for code generation and completion tasks
Meta's specialized code generation model
What's New in This Version
Specialized for code generation and completion tasks
Technical Specifications
Key Features
Capabilities
Other Meta Models
Explore more models from Meta
Muse Spark Open
Meta's open-weight frontier model — an 816B mixture-of-experts with 42B active, natively multimodal, built for coding and long-horizon agents, and able to run on two Mac Studios
Muse Wonder
Meta's first frontier-class model, closed-weight and built for personal and professional agents, with Active Memory across conversations and Active Focus on long goals; its larger sibling, Muse Wonder Full, is reserved for paid Muse Code subscribers
Muse Spark 1.3
Meta's most capable Muse model, built for long-horizon agentic work — it collaborates, asks before consequential actions, and holds complex instructions across multi-step tasks
