Phi-4 14B

Microsoft

Microsoft small language model excelling at math, reasoning, and STEM. Trained on heavily synthetic data. 7.3M+ Ollama pulls.

Text Generation Local Phi Family v4

Documentation Back to Models

Parameters

14B

params

Context Window

16K

tokens

Max Output

tokens

Input Price

per 1M tokens

Output Price

per 1M tokens

Phi Family Timeline 6 versions

Phi-4 Mini Reasoning Latest local

Apr 2025

Phi-4 14B Current local

Dec 2024

Phi-3.5 Mini local

Aug 2024

Phi-3 Mini 3.8B local

Apr 2024

Phi-3 Small 7B local

Apr 2024

Phi-3 Medium 14B local

Apr 2024

Capabilities

👁️

Vision

⚡

Function Calling

📋

JSON Mode

🌊

Streaming

💬

System Prompt

🖥️

Code Execution

🔍

Web Search

🔌

MCP Support

Local Model Specs

Quantization

Q4_K_M

Architecture

Dense Transformer

Runtime

Ollama / llama.cpp

Disk Size

9.1 GB

Details

Release Date: December 12, 2024
Knowledge Cutoff: -
Source: Local
License: MIT
Model ID: phi-4

Last updated: March 13, 2026