OSAIM
Open Source AI Models

Microsoft

Phi

Microsoft's small-language-model line, focused on data-quality-driven training. Phi-4 punches well above its weight class.

Visit homepage ↗

History & context

Microsoft's Phi line is built on a thesis: that careful curation of training data can extract frontier-class quality from much smaller models. Phi-1 (June 2023) was a 1.3B Python coder; Phi-2 (December 2023) was a 2.7B generalist; Phi-3 (April 2024) shipped at 3.8B (Mini), 14B (Medium) sizes.

Phi-4 (December 2024) was the standout: a 14B model trained primarily on synthetic data, with reasoning and math performance that exceeds models several times its size. It demonstrated that synthetic-data curation at scale could close the gap between small-data and large-data training regimes.

All Phi releases (3 and 4) ship under MIT — fully permissive open source. They're the most permissively-licensed strong-quality small models available.

Flagship model

3 models in this family

Comparing Phi against another family? Try the side-by-side comparator or browse all leaderboards.