Resource detail

Phi-3 Mini

Microsoft Research's compact model for local and edge inference.

OverseasFreeOpen source

Visit official siteMore like this

At a glance

phi-3-mini

Pricing

Free

Access

No login

Platforms

Web

Chinese support

Last checked

2026-08-29

Popularity

79/100

Model background

Open weights

Phi-3 Mini used textbook-quality data to show small models can reason well, reigniting interest in edge AI.

Why it mattered

Phi-3 Mini used textbook-quality data to show small models can reason well, reigniting interest in edge AI.

Official linkhttps://www.microsoft.com/en-us/ai

Model capabilities

Multimodal -Reasoning ✓Coding ✓Tool use ✓Long context ✓

Context length

128K tokens

Provider

microsoft

Typical use

端侧助手教育实验

Similar tools and resources

Selected by use case

Mistral 7B

A compact, capable, and easy-to-deploy open-weight baseline.

GlobalFreeOpen source+2

Updated 2026-08-29

Visit official site

Qwen2.5

A broad open family balancing Chinese, multilingual, and coding ability.

DomesticFreeOpen source+2

Updated 2026-08-29

Visit official site

GPT-5

OpenAI's flagship model with adaptive reasoning and fast responses.

OverseasPaidFlagship+2

Updated 2026-08-29

Visit official site

GPT-4o

OpenAI's multimodal model for general Q&A, vision, and tool use.

OverseasPaidMultimodal+2

Updated 2026-08-29

Visit official site

OpenAI o3

OpenAI's deep-reasoning model for math, science, and complex planning.

OverseasPaidReasoning+2

Updated 2026-08-29

Visit official site

Claude Sonnet 4

Anthropic's high-performance model for coding, long documents, and complex reasoning.

OverseasPaidLong context+2

Updated 2026-08-29

Visit official site