Runs in your browser. Nothing you enter is uploaded or logged.
Next steps
One useful email every Monday
New free tools, AI and network threats that matter, and one quick challenge. No spam, unsubscribe in one click.
How to use it
- 1
Enter your graphics or unified memory.
- 2
See which model sizes fit.
- 3
Install Ollama or LM Studio and run one.
Questions people ask
How much VRAM do I need for an 8B model?
About 7 GB at 4-bit with an 8K context, and about 11 GB at 8-bit.
Is running AI locally free?
The software is free and there is no per-token cost; you pay for hardware and electricity.
Related tools
- 15 ways to cut token costsCaching, batch, routing and output limits, with the official discounts behind each.
- Cheapest model for my taskPick a task and volume; see which model does it for the least per month.
- API bill estimator & budgetMonthly cost, caching and batch savings, and the day your budget runs out.
- AI subscription checkerWhich ChatGPT, Claude, Gemini or Copilot plans overlap, and what to cancel.
- Do I need a paid AI plan?Four questions tell you if Free, a $5–8 plan, $20 or $100+ fits.
Link to this tool
Found it useful? Paste this into your blog, wiki or runbook.
<a href="https://toolbini.com/ai/run-ai-locally/">Run AI locally (hardware check)</a>Reviewed by the editorial team · Last reviewed 2026-11 · Report an error