Skip to main content
⌘K

Phi-3 (Microsoft)

Microsoft compact open-weight models delivering strong performance at small sizes, ideal for low-resource air-gapped systems.

View on GitHub Official site
Llm Models MIT Low setup 1,700 stars

Overview

Plain English

Microsoft compact open-weight models delivering strong performance at small sizes, ideal for low-resource air-gapped systems.

Technical

Microsoft compact open-weight models delivering strong performance at small sizes, ideal for low-resource air-gapped systems.

Technical scorecard

License MIT
Commercial use Yes
OpenAI-compatible API No
REST API No
Fine-tuning support No
Quantization support No
Docker available No
GUI / no-code available No
Telemetry None
Offline after setup Yes

Data & Privacy

Does it send data online?

After setup, this listing is marked as usable offline. Confirm network behavior against the upstream project before regulated deployment.

Does it store history?

Not verified in this directory yet. Review the upstream docs for persistence, logs, and workspace storage.

License checks?

Commercial use is marked as allowed or likely allowed by the listed license.

Telemetry?

None

Last verified: Dec 10, 2025. Maintainer verification should be treated as directory guidance, not legal advice.

Setup & Installation

Low

GUI, low-resource, or simple install path likely available.

Prerequisites

Python, Docker, Bare Metal

# Start with the official project documentation
# https://huggingface.co/microsoft/Phi-3-mini-128k-instruct

Hardware Requirements

RAM8 GB minimum / 16 GB recommended
Hardware tagsCPU Only, NVIDIA GPU (CUDA), Low-resource (< 8GB RAM)
Model formatsGGUF, Safetensors
Primary languagePython

Works Well With