Best AI Mini PCs for Local LLM

The Mac mini M4 Pro is a five-inch-square box with a 12-core CPU, a 16-core GPU and 64 GB of unified memory, and it runs near-silently on very little power. PCMag rated it 4.5 out of 5 and Macworld 4 out of 5, landing on the same split verdict: the machine is excellent and the configuration pricing is not. For local-LLM work the 273 GB/s of memory bandwidth is the number that matters, and 64 GB is the hard ceiling that comes with it. Nothing inside is upgradable, so the configuration you buy is the one you keep.

If the requirement is fitting a 120B-parameter model locally, the GMKtec EVO-X2 is the 128 GB-class mini PC to buy. PCWorld praised its 'excellent combination of CPU, GPU, and NPU performance at desktop workstation level' and scored it 4.5/5. The XDNA 2 NPU contributes 50 TOPS toward a 126 TOPS platform total once the Ryzen AI Max+ 395 and the Radeon 8060S iGPU are counted. With 128 GB of LPDDR5X at 256 GB/s it loads GPT-OSS 120B Q4 with room to spare and runs 70B-class models at 6-8 tokens/sec for a single user. Memory is soldered, and a single 2.5G Ethernet port limits clustering.

The Framework Desktop puts AMD's Strix Halo silicon into an open, repairable chassis aimed squarely at local AI. PCWorld awarded it 4.5/5 and an Editors' Choice, writing that 'it's not just for tinkering, this machine can legitimately run the latest AI models locally, something few desktops this size can do.' Of its 128 GB of LPDDR5X-8000 unified memory, AMD's driver can assign up to 96 GB as VRAM, enough to run GPT-OSS 120B, which AMD says runs about ten times faster than Llama 3 70B on this chip. ServeTheHome called it 'our third-favorite AMD Strix Halo mini PC so far,' and Tom's Hardware noted 'the mix of powerful graphics and plentiful RAM is why Framework is pushing this as an AI system.' Windows and Linux both run on it, so the full open-source AI stack is available in a way it isn't on the Mac Studio. Bandwidth and price are the limits.