DeepSeek-Coder
Open-weight code LLM trained on 2 trillion tokens of code and natural language.
About
DeepSeek-Coder is a family of open code models trained from scratch on two trillion tokens that are 87 percent code and 13 percent natural language in English and Chinese, released in 1.3B, 6.7B, and 33B sizes. Each model uses a 16K context window and a fill-in-the-blank objective to support project-level completion and infilling. Released under the DeepSeek 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
- DeepSeek License
- 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.