Best Mini PC for Local LLM?

Mac Mini M4 Leads on Speed and Efficiency

The Mac Mini M4 achieves ~18 tokens per second on a 7B Q4 model, consumes ~30 W under load, and starts at approximately 599 USD — making it the fastest mini PC for local LLM inference. The M4 chip uses unified memory architecture, meaning the same physical RAM is shared between CPU and GPU with no memory copy overhead. For users prioritizing speed, the M4 is the top choice.

The Minisforum UM790 Pro is the scaling option: AMD Ryzen 9 7940HS with Radeon 780M iGPU, up to 64 GB DDR5 configured as unified memory, and ~8 tok/s on Linux with ROCm. The Beelink SER8 (Ryzen 9 8845HS) matches the UM790 Pro on throughput but uses CPU-only inference — no discrete GPU required — making it the budget-friendly choice for users on Windows or Linux who want to avoid ROCm setup.

Apple announced a next-generation Mac mini lineup on August 25, 2026, shipping September 22, 2026: the M6 chip starts at $899 with a 32 GB unified memory maximum, and the M5 Pro chip starts at $1,699 with a 64 GB unified memory maximum. Apple has not published independent LLM benchmarks for either chip; Apple's own marketing claims up to roughly 4x the AI performance of the M4, but that figure comes from Apple, not third-party testing. If you are buying today, compare the discounted M4's price against these new starting prices before deciding.

The table below compares the three mini PCs across CPU/GPU, best memory configuration, and measured LLM speed.

Unified Memory Is the Key Differentiator for LLM Performance

Standard mini PCs with discrete GPU slots are not useful for LLM inference because the GPU VRAM is fixed at the factory — typically 4–8 GB — and cannot be expanded. The Mac Mini M4 and UM790 Pro solve this via GPU-based inference with unified memory. The Beelink SER8 takes a different approach: its Ryzen 9 8845HS uses CPU-only inference, which is slower but requires no GPU setup.

The Mac Mini M4 with 16 GB unified memory outperforms the UM790 Pro with 32 GB DDR5 on raw inference speed because Apple's memory bandwidth (~68 GB/s) and Metal GPU acceleration are more efficient than the Radeon 780M iGPU. The UM790 Pro's advantage is the ability to expand to 64 GB, which allows running larger models such as 13B and 30B Q4 that do not fit in 16 GB. Among the new Mac mini chips, only the M5 Pro reaches 64 GB — the base M6 tops out at 32 GB, a step down from the outgoing M4 Pro's 64 GB ceiling. Readers who want to match the UM790 Pro's 64 GB memory on a Mac mini now need the M5 Pro specifically, not the base M6.

For a full guide to hardware selection for local LLM, see the best Ollama frontend overview which covers the software side of local LLM setup.

For Japan-specific mini PC recommendations with Amazon.co.jp links and JPY prices, see our best mini PC for local LLMs in Japan guide.

Related Guides

• ▸Best SSD for Fast Model Loading -- best SSD for fast model loading
• ▸Strix Halo + Ollama + Vulkan: Performance Guide -- Strix Halo Ollama Vulkan setup