Local

What is Local?

Local is an Inference tool that runs AI on-device with fast, private infrastructure. It is available on macOS. It is aimed at developers, ai researchers and privacy-focused users.

Base Compute is an AI inference lab focused on building inference engines and infrastructure for running powerful AI on-device. It offers fast, private, and cost-effective solutions for deploying AI models directly on local machines.

Built for developers, ai researchers, privacy-focused users and enterprise teams.

Key capabilities

• Coding

Features

• On-Device AI Runtime

  Runs AI models directly on local machines for privacy and speed

• Private AI Infrastructure

  Provides secure, private AI deployment without cloud reliance

• Fast LLM Runtime

  Optimized for high-speed execution of large language models on Apple Silicon

• Model Decoding Tools

• Developer Tools

  Includes APIs and SDKs for AI infrastructure development

• AI Agent Support

  Enables deployment of AI agents and assistants locally

Use cases

• Deploy AI models directly on local machines for privacy
• Run large language models with high-speed performance
• Utilize model decoding tools for specific AI models

Pros & cons

AI models

• Llama 3.2
• Qwen 3

Developer & API

Security & compliance

• SSO

As stated on Local's website — not independently verified by AiByts.

FAQ