AI hosts for self-hosted agents.
Raspberry Pi, Mac mini, Intel NUC, mini PCs, refurbished phones: one spec sheet per device, with what it can run and what it costs. Local-model speeds, where a page gives one, are published measurements with their source. Which one to buy at which budget: the hardware buyer's guide.
By price, lowest first
The PocketClaw origin story device. €15-30 used. Runs lightweight agents via Termux + proot, with serious caveats.
€20 SBC with 512 MB RAM. Useful as an edge agent endpoint (sensor reader, tool host) but not a primary agent host.
Raspberry Pi 5 for self-hosted AI: four Cortex-A76 cores, 1 to 16 GB of LPDDR4X. Hosts Hermes Agent (no browser tool) or Nanobot; local models up to about 3B.
€100-180 used Intel mini PC. 8th gen i5, 8-16 GB RAM, NVMe. The cheapest credible mini PC for self-hosted AI.
Orange Pi 5 Plus: Rockchip RK3588, 4, 8 or 16 GB of LPDDR4/4X and a 6 TOPS NPU. The Raspberry Pi 5's closest competitor for self-hosted AI on ARM.
Lenovo ThinkCentre M75q, used: a €150-250 Ryzen mini PC with 16 GB of RAM and an NVMe slot, enough for Hermes Agent with the browser tool.
The Khadas Edge2 in its Pro configuration: Rockchip RK3588S2, 16 GB of LPDDR4X and 64 GB of eMMC on a small board. Polished hardware, smaller community.
Sub-€300 fanless Intel N100 mini PC with 16 GB RAM. The silent always-on tier.
Intel NUC 13 and Geekom IT13: 13th-gen Intel Core mini PCs with 16 to 64 GB of RAM, room for Hermes Agent with browser automation and a 7B model beside it.
Mac mini M4 and M4 Pro for local LLMs: 16 to 64 GB of unified memory at 120 or 273 GB/s, the two specs that decide which models load and how fast.
Minisforum UM790 Pro: Ryzen 9 7940HS with Radeon 780M graphics and up to 64 GB of DDR5, for a Linux agent host that also runs local models.
Repairable, modular laptop with strong Linux support. The right choice if you want a portable agent host that doubles as a daily driver.
Fanless laptop with up to 24 GB unified memory. Runs Mistral 7B Q4 silently on the train. €1,299+.
Apple's 2025 local-LLM workstation: M3 Ultra, 96 GB of unified memory configurable to 256 GB, 819 GB/s. Since replaced by the M5 Ultra model.