Devices for local AI

1 refurbished laptops, desktops, and mini PCs — classified by AI capability. No cloud. Ships same day from Reno, NV.

1 device · Tablet/2-in-1

Runs small models

Phi-4 Mini 3.8B · Llama 3.2 3B· 10–20 tokens/sec via Metal

1 available
MS Surface Pro 4 1724 12.3"2736x1824 TOUCH m3-6Y30 900MHz 4GB 128GB SSD Win10ProTablet/2-in-1
Runs small models

Microsoft

MS Surface Pro 4 1724 12.3"2736x1824 TOUCH m3-6Y30 900MHz 4GB 128GB SSD Win10Pro

Device$79.99
+ 16GB DDR4 RAMfrom $44.99
AI-ready total~$124.98
View device →
Upgradeable

Add 16GB RAM — AI-ready total from ~$79.99

1 available
MS Surface Pro 4 1724 12.3"2736x1824 TOUCH m3-6Y30 900MHz 4GB 128GB SSD Win10ProTablet/2-in-1
Runs small models

Microsoft

MS Surface Pro 4 1724 12.3"2736x1824 TOUCH m3-6Y30 900MHz 4GB 128GB SSD Win10Pro

Device$79.99
+ 16GB DDR4 RAMfrom $44.99
AI-ready total~$124.98
View device →

How to run AI locally

1

Pick a device

Filter by tier, brand, or type.

2

Install Ollama

Free. ollama.com. 2 minutes.

3

Pull a model

ollama run llama3

4

Chat privately

Nothing leaves your machine.

Common questions

What laptop can run Llama 3 locally?

Any laptop with 16GB RAM can run 7B–8B models like Llama 3.2. For 70B models you need 32GB or Apple Silicon.

Do I need a GPU for local AI?

No. 7B–8B models run on CPU with 16GB RAM. A GPU helps for larger models but is not required.

Do desktops and mini PCs work?

Yes. A Dell OptiPlex or Intel NUC with 16GB RAM runs 7B models well. Gaming PCs with RTX GPUs handle 13B–32B models.

How do I start after buying?

Install Ollama from ollama.com (free, 2 min). Run "ollama pull llama3". Done — runs 100% locally.