CodeLlama
Code-specialized Llama model by Meta for code generation and understanding.
About
Code Llama by Meta is a family of code-specialized language models built on Llama 2, offering foundation models, Python-focused variants, and instruction-following models at 7B, 13B, and 34B parameters. They support code infilling, zero-shot instruction following for programming, and large input contexts, trained on 16k-token sequences with stable behavior on inputs up to about 100k tokens. Released under the Llama 2 Community License.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Llama 2 Community
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Open-source code LLM family by IBM for enterprise code generation.
High-performance open-weight MoE LLM with 671B total parameters.
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
State-space model for language with linear-time sequence modeling.
Family of small language models by Hugging Face for on-device use.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.