Microsoft
Phi 4 Mini Instruct
Developed by Microsoft, Phi 4 Mini Instruct is a chat model capable of handling various tasks such as function calling, reasoning, and text generation. It is notable for its large context window of 131,072 tokens, allowing it to process and understand extensive conversations or texts.
Input
Output
Context
131K
Max Output
4K
Parameters
3.8B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens4,096 tokens
Parameters3.8B
Release DateFeb 19, 2025
Training CutoffJun 1, 2024
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.2%
HLE
3.0%
AIME
33.1%
GPQA
10.8%
SciCode
69.6%
MATH 500
46.5%
MMLU Pro
6.7
Math
3.6
Coding
12.6%
LiveCodeBench
3.0
Intelligence
46.2
Speed (tok/s)
1.3
TTFA (s)
1.3
TTFT (s)
Resources & Links
Estimated GPU Requirements for Phi 4 Mini Instruct
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.