Specs at a glance
| CPU | Intel Core i5/i7 13th gen, 10-14 cores (Geekom IT13: i7-13620H, 10 cores) |
| RAM options | 16 / 32 / 64 GB DDR4 / DDR5 |
| Storage | NVMe SSD 256 GB to 2 TB |
| Power draw | 15-55 W |
| Form factor | 117 × 112 × 38 mm |
| Local LLM capability | Up to 13B Q4 |
| Price point | €300-600 |
Choosing between devices? The hardware buyer's guide compares them by budget, and Local LLM benchmarks has the published speeds, machine by machine.
Overview
Two takes on the same class of machine: Intel's NUC 13 reference design, now built by ASUS, and the Geekom IT13, a generic box with an i7-13620H usually sold with 32 GB of RAM and a 1 TB SSD. 32 GB runs Hermes Agent with every tool, the Chromium browser tool included, with room for a 7B model as a local fallback (a 4 to 5 GB download at 4-bit in the Ollama library). Local-model speed comes from the integrated graphics, and llama.cpp's Vulkan scoreboard has no entry for 13th-generation Intel Core chips; on the same 7B test, Intel's Core Ultra 100 series writes 8.21 tokens per second and AMD's Ryzen 7000 series 19.91. Pick the NUC for the reference design (BIOS stability, procurement, vendor support); pick a Geekom, Beelink or Minisforum box for the price. Which machine to buy at which budget is in the hardware buyer's guide.
Best for
- Hermes Agent with browser automation
- Multi-user team agents at small scale
- A 7B local model (Q4) next to the agent
- ZeroClaw with Mistral 7B / Llama 3 8B
- Geekom IT13: the same class of machine for less than the NUC
Not for
- Truly portable use (mains power assumed)
- Larger local models (>7B), needs Mac Studio or GPU
- Always-on if power budget is tight
Compatible self-hosted agents
Listed as compatible with Intel NUC 13 and Geekom IT13 from each agent's requirements, not from a test (with the caveats from “Best for” / “Not for” above):
Where to buy
The Amazon link is an affiliate link: it costs you nothing and funds the site. Details on our disclosure page.
See also: all AI hardware · AI agents tracker · AI CVEs · edge AI hardware buyer's guide · scan your AI stack · our methodology.