Phi is Microsoft’s small open-weight language model family. Phi models punch well above their parameter count on reasoning benchmarks and are designed for edge and on-device inference.
See all models from MicrosoftModels in family
1
Open weight
1
API only
0
Avg score
64.9
Top benchmark
—
Total HF downloads
388.0K
Primary modality
Text
First release
Feb 2025
Latest release
Feb 2025
Every release in the Phi family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB64.9 | 5.6B | Feb 2025 |
When each release shipped, newest first. Useful for tracking version cadence.
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB64.9 | 5.6B | Feb 2025 |
Spin up an instance in the cloud, or pick local hardware that fits.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Provider
See every model from a lab side by side, with aggregate stats. Useful when you want a cross-family view of one provider.