← Back to Tools

XIALEI TOOLBOX · PUBLIC BETA

Your local AI.
A simpler setup.

Install Ollama with a small, readable DevOps toolkit. Choose your platform, approve the installation, and start exploring models on your own computer.

Download installer toolkit · ZIP

Free download · No signup · No bundled AI models

Choose your platform

MACOS

Mac

Extract the ZIP and open Install Ollama.command. Keep the downloaded files together. Type YES when prompted; the official installer may ask for administrator permission.

If macOS blocks the script, use Ollama’s official installer rather than disabling Gatekeeper.

Official Mac download ↗

WINDOWS

Windows

Extract the ZIP. Right-click install-ollama-windows.ps1 and choose Run with PowerShell. Approve the prompt. The toolkit checks the official installer’s digital signature before starting installation.

If your security policy blocks unsigned scripts, use the official installer instead.

Official Windows download ↗

LINUX

Linux

Ask your administrator to run the included install-ollama.sh script with sh. It checks the operating system and processor, requests your consent, then downloads and runs Ollama’s installer.

A compatible 64-bit system, internet access and curl are required. Administrator permission may be requested.

Official Linux instructions ↗

LINUX ENVIRONMENT REQUIRED

ChromeOS / Chromebook

Chrome itself cannot run this installer. On a compatible Chromebook, enable Settings → Developers → Linux development environment, then use the Linux script inside that environment.

School or work devices may restrict this. GPU acceleration is not guaranteed; CPU-only performance depends on your hardware.

After installation

  1. Check Ollama is available. Open the app or a new terminal. The installer also attempts a version check.
  2. Choose an AI model. Models are a separate download and can use several gigabytes of storage and memory. Start small on modest hardware.
  3. Keep it private. This toolkit does not configure public API access. Do not expose your local Ollama service to the internet without authentication.
Follow Ollama’s getting-started guide ↗
What this beta does—and does not do

Already-installed Ollama is left unchanged. Failed downloads stop installation. Windows checks the executable’s publisher signature; Mac and Linux fetch the official shell installer over HTTPS, without an independently pinned checksum. Official installer behavior and requirements may change.

This is a convenience toolkit, not an official Ollama product or a version-pinned enterprise deployment system. It does not install GPU drivers separately, download models, create accounts, or configure your firewall. See the included README for limitations and troubleshooting.