Deepseek Coder 33B Base
DeepSeek develops the Deepseek Coder 33B Base, a chat model exceling at project-level code completion and infilling tasks, thanks to its pre-training on a large project-level code corpus with a window size of 16K and an extra fill-in-the-blank task. This 33B parameter model, utilizing Grouped-Query Attention, was trained on 2 trillion tokens comprising 87% code and 13% natural language in both English and Chinese.
Input
Output
Context
16K
Max Output
16K
Parameters
33B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek Coder 33B Base
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.