TextImage + text

Phi

Small Microsoft models trained on carefully selected data: strong at logic and math for their modest size. Versions with images and speech are available.

Developer
Microsoft, USA
First release
Sep 2023
Latest release
Jan 2026
Sizes
1.3B – 42B-A6.6B
License
Commercial use allowedMIT
Russian
Supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Education, Finance, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Assistant on a laptop or your own server
  • Reasoning and calculation tasks
  • Analysis of images and diagrams (vision versions)
  • Classification and data extraction

Where it is used

Internal company servicesEducationAnalytics

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Phi-4-reasoning-vision-15B
  2. Phi-4-reasoning
  3. Phi-4-mini и multimodal
  4. Phi-4
  5. Phi-3.5 (включая MoE и Vision)
  6. Phi-3
  7. Phi-2
  8. Phi-1 / Phi-1.5

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Phi be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Phi need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Phi support Russian?

Yes, Russian is listed on the model card.

Where can I download Phi and what does it cost?

The Phi weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Comparisons

Similar models

TextGemmaGoogle · USACommercial use allowed

Compact Google models that run well on a single computer; larger versions understand images. Includes CodeGemma for code, FunctionGemma 270M for function calling and the fast DiffusionGemma.

DetailsTextSmolLMHugging Face · USACommercial use allowed

Tiny open Hugging Face models for phones and laptops. SmolLM3 (3B) can reason and handle long context; the full training recipe is open.

DetailsTextIBM GraniteIBM · USACommercial use allowed

IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.

Details

Source: huggingface.co/microsoft/Phi-4-reasoning-vision-15B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.