Tools

Local AI checker

Can this computer run local AI?

Let Taby take a quick look at what your browser can safely share, then get a plain answer for local chat, voice, coding, notes, and Taby's local brain.

No download. No account. The browser keeps exact details private, so VRAM and some chip names may still need a quick correction.

Ready when you are

One click check

Click the button and Taby will estimate the best local AI tier for this machine.

Local AI fit--

Recommended model tier

Waiting for this computer

Taby brainVoiceCoding

What do you want local AI to feel good at?

This changes the recommendation without making you fill out a giant form.

How the estimate works

The checker weighs RAM, Apple unified memory, GPU VRAM, CPU-only fallback, and the kind of AI job you want to run. It is intentionally conservative because context length and quantization can change memory use.

What counts as local AI

Local AI means the model runs on your own computer instead of sending every prompt to a hosted model. That can be useful for private notes, tasks, habits, voice commands, and offline-first workflows.

Taby fit

Taby is designed around a private local AI brain for planning your day and working with your tasks. This checker helps you understand whether your computer is ready for that style of assistant.

Quick guide

What specs do you need for local AI?

For most people, the practical starting point is a small or standard local model: 3B, 4B, 7B, or 8B parameters in a quantized format. These are small enough to run on many modern laptops while still being useful for summaries, planning, notes, and everyday chat.

GPU memory matters most on Windows and Linux. A dedicated GPU with 6GB to 8GB VRAM can usually handle smaller local models, while 12GB to 16GB opens up more comfortable 7B, 8B, and some 14B workflows. CPU-only can work, but it often feels slower.

On Apple Silicon Macs, unified memory is the important number. An 8GB Mac can try small models, 16GB is a stronger baseline, and 32GB+ gives you more room for better models, longer context, and normal apps running at the same time.

Read what local AI can do