Phi 4
Developed by Microsoft, Phi 4 is a chat model capable of handling various tasks such as function calling, reasoning, and text generation. It is genuinely best at processing long sequences of text, thanks to its large context window of 16,384 tokens.
Input
Output
Context
16K
Max Output
16K
Parameters
14.7B
Technical Specifications
Model TypeChat
Context Window16,384 tokens
Max Output Tokens16,384 tokens
Parameters14.7B
Release DateDec 11, 2024
Training CutoffJun 1, 2024
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.1%
HLE
14.3%
AIME
57.5%
GPQA
26.0%
SciCode
81.0%
MATH 500
71.4%
MMLU Pro
18.0
Math
11.2
Coding
23.1%
LiveCodeBench
4.9
Intelligence
32.5
Speed (tok/s)
0.526
TTFA (s)
0.526
TTFT (s)
Resources & Links
Estimated GPU Requirements for Phi 4
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.