Phi-4 Mini
Ultra-compact model with strong reasoning
Phi-4 Mini is a 3.8-billion parameter model that delivers impressive performance on mathematics and code for its size. It is ideal for on-device inference, edge deployments, and latency-critical applications where a larger model would be impractical.
Try Phi-4 MiniSpecifications
Context window16k tokens
Input price$0.030 / 1M tokens
Output price$0.060 / 1M tokens
Credits per query2 cr
Released2025-02
LicenseMIT
Features
Tool useJSON modeCode
Benchmark Scores
What do these mean?Sourced from official model cards and academic papers. Higher is better.
,
,
,
75%
72%
78%
,
,
Run locally
Download and run this model on your own hardware, no API key or internet required after setup.
Min VRAM3 GB
Rec. VRAM4 GB
Best VRAM6 GB
Parameters3.8B
Speed~85 tok/s
Context128K tokens
Ollama
TerminalRun this command in your terminal. Ollama downloads and manages the model locally.
ollama pull phi4-mini