This is my next mini PC.
The Mac mini (M6, 16GB), ₹99,900.
I don’t want a second desktop, I want a machine small and quiet enough that I forget it’s on, doing the one job I don’t want my gaming rig awake for.”
It’s for the one job I don’t want my desktop doing
My desktop is built for gaming and heavy lifting, not for sitting on 24/7 running a local model or serving files to my phone. Every time I’ve left it on overnight for that, it’s felt like using a truck to fetch the mail. I want something small enough to just leave running.
The M6’s unified memory is actually built for this
Apple’s own numbers put the M6 at up to 4x faster for AI tasks than the outgoing M4, with 170GB/s of memory bandwidth feeding it. That’s the number that matters for running a model locally, not the core count, and it’s the first Mac mini I’d trust with that job.
Silent and cheap enough to just leave on
A mini idles at a few watts and makes no noise doing it. My desktop’s fans spin up the moment anything real is running on it. For a box that’s meant to just sit there working in the background, that difference is the whole point.
| Chip | Apple M6, 12-core CPU / 12-core GPU, 16-core Neural Engine |
|---|---|
| Memory | 16GB unified, 170GB/s bandwidth (configurable to 32GB) |
| Storage | 256GB SSD (base config) |
| Ports | 3× rear Thunderbolt 4, HDMI, 2× front USB-C, 2.5Gb Ethernet |
| Wireless | Wi-Fi 7, Bluetooth 6 |
| Size | 12.7 × 12.7 × 5 cm |
Beelink SER9 Pro (Ryzen AI 9 HX 370), if you want a similar always-on AI box on Windows or Linux, with an NPU of its own, and don’t need macOS.
If you buy through that link I earn a small commission. It costs you nothing and keeps the picks independent. I accept long-term review units; they never buy the pick, and I say so when a unit was loaned.
Why not just run local AI models on the desktop I already have?
I could, but it means keeping a power-hungry gaming rig on around the clock for a background job. The mini is built to idle at a few watts and stay silent doing it, which is what an always-on box should do.
Is 16GB of unified memory actually enough to run local LLMs?
Comfortably for 7B–8B models, which covers most of what I’d actually use day to day. Anything bigger means stepping up to the 24GB or 32GB configuration, or the M5 Pro model if I outgrow this one.
Why Apple silicon over a cheaper x86 mini PC?
Mostly efficiency per watt for a box that’s on all day, plus Apple’s MLX framework runs well on the M-series chips. If you don’t need macOS, something like the Beelink SER9 Pro gets you a real NPU for less.