Phi 2
Developed by Microsoft, Phi 2 is a Transformer-based chat model with 2.7 billion parameters, exceling at tasks such as code generation, function calling, and text generation, particularly in QA, chat, and code formats. Its context window of 2,048 tokens allows for complex and nuanced interactions.
Input
Output
Context
2K
Max Output
0K
Parameters
2.8B
Technical Specifications
Model TypeChat
Context Window2,048 tokens
Max Output Tokens256 tokens
Parameters2.8B
Release DateDec 13, 2023
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Phi 2
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.