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-weight models by Google in 2B, 9B, and 27B sizes with strong performance.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.
Open-weight LLM family by Alibaba with strong multilingual and coding abilities.
Small language model by Microsoft in 3.8B size with strong benchmark performance.
Open-access 176B parameter multilingual LLM by BigScience supporting 46 languages.
Retrieval-augmented generation optimized LLM by Cohere with 128K context.