Skip to main content

Microsoft · Text

Phi models: Versions, specs, GPU requirements & hosting

Microsoft Phi targets compact reasoning and instruction-following deployments where model size and operational efficiency matter.

Technical deployment reference illustration for Phi
Reference deployment flow; exact architecture facts are listed separately.

Overview and history

Phi is an official Microsoft model family represented here through independently verified release, checkpoint, license, runtime and hardware evidence. Microsoft Phi targets compact reasoning and instruction-following deployments where model size and operational efficiency matter. Current public releases are grouped by the General, Reasoning Vision tracks so sibling sizes and specialist branches are not presented as false chronological generations.

FusionPointAI currently tracks 2 certified public Phi releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.

Compact model sizes
Reasoning variants
Broad inference support

Architecture and model range

The verified public range spans 3.8B to 15.1B total parameters and context windows up to 131,072 tokens. Each release states whether it is dense or mixture-of-experts and records active parameters separately when the official source publishes them.

Public releases2
Model tracks2
Current generationPhi-4 Reasoning Vision 15B
Last verified2026-09-03T00:00:00.000000Z

Deployment ecosystem

Choose a specific Phi release and certified checkpoint before sizing hardware. FusionPointAI rejects unknown runtime configurations, calculates resident memory from total model weights, then distinguishes globally compatible GPUs from currently rentable inventory.

Validate the exact checkpoint license, runtime version, precision kernel, context length, concurrency and multi-GPU topology. Active MoE parameters affect compute, but resident model memory continues to use total stored weights.

Common use cases

Edge-to-server assistants
Developer tools
Efficient private inference

License overview

Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.

Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.

Release timeline

microsoft/phi/phi-4-mini @ f79166923a03646efde5aa2c4b86837297c6ab419752f980c51f2e0325778f1c

Official source

microsoft/phi/phi-4-reasoning-vision-15b @ 774fca2dd44129960f036e3654fe9b6da48eaae80b2b09d1b8f6e667e99e427a

Official source

Frequently asked questions

Which Phi release is current?

Current releases are Phi-4 Mini, Phi-4 Reasoning Vision 15B, evaluated within their respective tracks.

Can Phi be self-hosted?

Only releases with a verified official checkpoint and supported runtime configuration are presented as deployable.

Which GPU should run Phi?

GPU selection depends on the exact variant, checkpoint precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.

Official references

Last verified: 2026-09-03