Code Llama 34B
MetaMeta's specialized coding model built on Llama 2. Excels at code generation, completion, and debugging across multiple programming languages.
Parameters 34B
Min VRAM 20 GB
Recommended VRAM 24 GB
Context Length 16K
License Llama 2 Community
🚀 Get Started
Run Code Llama 34B locally with one command:
ollama run codellama:34b Requires Ollama installed.
📊 Benchmarks
BenchmarkScore
HumanEval 48.8
MBPP 55.0
MultiPL-E 45.1
💻 Hardware Recommendations
🟢 Minimum
20 GB VRAM GPU or 40+ GB RAM (CPU mode)
Expect slower generation in CPU mode
🔵 Recommended
24 GB VRAM GPU
Fast generation with room for context