Free & Open Source

Private AI on Your Laptop.
No Subscription. Ever.

One free script installs a complete AI stack on any Mac or Windows laptop in about 20 minutes. Works offline. Nothing leaves your device.

MAC — TERMINAL
curl -s https://gotlaptopparts.com/ai-setup/mac.sh -o /tmp/ai-setup-mac.sh && bash /tmp/ai-setup-mac.sh
WINDOWS — POWERSHELL
irm https://gotlaptopparts.com/ai-setup/windows.ps1 -OutFile "$env:TEMP\ai-setup.ps1"; powershell -File "$env:TEMP\ai-setup.ps1"

What you get

Everything runs privately on your laptop.

🖥️
AI Chat
Like ChatGPT — runs locally. Ask anything. Works offline.
🌐
Browser AI
AI on every webpage. Summarize, translate, explain anything.
📄
Document AI
Drag any PDF or file. Ask questions about your documents.
System-wide AI
Highlight text in any Mac app. Press a shortcut. AI responds.
🔒 Completely private

Everything runs on your laptop. Your prompts, documents, and conversations never leave your device. No company — including GotLaptopParts — can see what you discuss. The script is fully open source. Read every line before running.

How it works

Four steps. Most of it runs while you walk away.

1
Choose your audience
The script asks who this is for: Personal use, Developer, or Business. Personal installs the full AI stack with a simple experience. Developer adds VS Code, Continue.dev, and Cline for local AI coding.
2
Name your AI (optional)
For personal use, give your AI a name — Aria, Max, Nova, or anything you like. The name is set as a system prompt so your AI introduces itself correctly.
3
Walk away while it installs
The script installs Ollama, LM Studio, Jan.ai, AnythingLLM, and Page Assist. It detects your hardware and downloads the best AI model automatically. Takes about 20 minutes on fast internet.
4
Start using your AI
Double-click "Start AI" on your Desktop to open LM Studio and chat. Check the browser tab that opened to add AI to Chrome, Firefox, or Edge. Open AnythingLLM to chat with your documents.

What gets installed

All free. All open source. No accounts required.

OllamaThe AI engine. Runs all models locally.
Source ↗
LM StudioChatGPT-style chat interface. No account needed.
Source ↗
Jan.aiFully offline chat. No telemetry at all.
Source ↗
AnythingLLMChat with PDFs, Word docs, any file.
Source ↗
Page AssistAI in Chrome, Firefox, Edge on every webpage.
Source ↗
Continue.devGitHub Copilot alternative for VS Code. Free.
Source ↗

Which AI model for your hardware

The script detects your RAM and installs the best model automatically.

Your RAMModel installedBest for
48GB+Llama 3.1 70BMaximum quality
24–47GBQwen3 32BNear-frontier quality
12–23GBLlama 3.1 8BFull quality, everyday use
6–11GBPhi-4 MiniFast, lightweight chat

After setup, switch to any of 200+ models inside LM Studio → Discover. No command line needed.

Frequently asked questions

How do I run AI locally for free on my laptop?

Run our free setup script — one command in Terminal (Mac) or PowerShell (Windows). It detects your hardware, installs Ollama, LM Studio, Jan.ai, and AnythingLLM, downloads the best AI model for your system, and has everything working in about 20 minutes. No account required. No subscription.

Is local AI as good as ChatGPT?

For most everyday tasks — writing, summarizing, answering questions, document review — local AI models in 2026 are comparable to ChatGPT. On hardware with 32GB+ RAM or a dedicated GPU, models like Qwen3 32B or Llama 3.1 70B produce near-frontier quality. The main difference: local AI never has rate limits, never goes offline, and never sees your data.

Does local AI work without internet?

Yes. Once the model is downloaded during setup, your AI works completely offline — on planes, in areas with no WiFi, anywhere. Nothing requires an internet connection after the initial setup.

Is this script safe to run?

The script is fully open source at github.com/gotlaptopparts/free-local-ai — read every line before running. It installs software only via Homebrew (Mac) and winget (Windows), both verified signed package managers. It never collects data, never connects to GotLaptopParts servers, and never installs tracking or telemetry of any kind.

What AI subscriptions does local AI replace?

Local AI can replace ChatGPT Plus, Perplexity Pro, GitHub Copilot, Claude Pro, and Grammarly Premium. The tools installed — LM Studio for chat, Page Assist for browser AI, Continue.dev for coding, and AnythingLLM for document chat — cover the same use cases as all of these paid services. Your actual savings depend on which subscriptions you currently pay for.

How much RAM do I need for local AI?

Minimum 6GB RAM for basic AI (Phi-4 Mini). 12GB for full quality (Llama 3.1 8B). 24GB for near-frontier quality (Qwen3 32B). 48GB+ for maximum capability (Llama 3.1 70B). Apple Silicon Macs are especially efficient — a MacBook Pro M2 with 16GB runs Llama 3.1 8B at 30–80 tokens per second.

Does it work on Apple Silicon (M1/M2/M3/M4)?

Yes — Apple Silicon is the best hardware for local AI. Metal GPU acceleration is automatic. The script detects your chip and configures everything optimally. A MacBook Pro M3 with 16GB RAM runs Llama 3.1 8B smoothly for all everyday tasks.

Can I switch AI models after setup?

Yes. Open LM Studio, click Discover, and browse 200+ free models. Download any with one click — no command line needed. Different models excel at different tasks: Qwen3-Coder for programming, DeepSeek R1 for reasoning, Gemma 4 for image understanding, Phi-4 Mini for fast lightweight chat.

Want it pre-installed?

We sell refurbished laptops with everything configured, model pre-downloaded, and verified working before shipping. Turn it on — AI works immediately.

Shop AI-Ready Laptops →
Need help?

Something not working? Call us or visit our help page.

📞 (775) 203-1085Help PageView Source
Need help finding a part?Ask Sara — describe your laptop or part number