Deepseek Coder 6.7B Base
DeepSeek develops the Deepseek Coder 6.7B Base, a chat model exceling at code completion, generation, and review tasks, thanks to its training on a massive 2T token dataset comprising 87% code and 13% natural language. Notably, this model boasts a large context window of 16,384 tokens, enabling it to handle project-level code tasks.
Input
Output
Context
16K
Max Output
-
Parameters
6.7B
Technical Specifications
Model TypeChat
Context Window16,384 tokens
Max Output TokensNot available
Parameters6.7B
Release DateOct 23, 2023
Training CutoffMay 1, 2023
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek Coder 6.7B 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 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.