16GB should be enough for TTS/Voice models running locally no ? I was thinking about having a home assistant setup like that where the voice is local and the brain is API based

No one is buying a base model Mac for local LLM. Everyone is forgetting the PC prices have drastically increased due to RAM and SSD. Meanwhile, Macs had no such price change… at least for the models that didn’t just drop today. Mac’s are just a good deal at the moment.

It's not cheap, though. Two weeks ago I bought a computer with a similar form factor (GMKtec G10). Worse CPU and GPU but same 16GB memory and a larger SSD for 40% the price of a base mac mini ($239 vs $599). It came with Windows preinstalled, but I immediately wiped that to install linux. Even a used (M-series) mac mini is substantially more expensive. It will cost me about an extra penny per day in electricity costs over a mac mini, but I won't be alive long enough for the mac mini to catch up on that metric.

I considered the mac mini at the time, but the mac mini only makes sense if you need the local processing power or the apple ecosystem integration. It's certainly not cheaper if you just need a small box to make API calls and do minimal local processing.

Worse than that, they hold their value, so buying a used M1 mini is still a few hundred bucks, and saving $200-300 by purchasing a 5 generation older mini seems like a bad deal in comparison.

Just like with GPUs and Bitcoin they'll be a flood of old hardware on the market eventually.

Not if you want it to be able to use the hardware identifiers to register for use with iMessage.

You aren’t going to run a network connected 24/7 online agent from a laptop because it’s battery powered and portable.

It’s what a small business might have paid for an onprem web server a couple of decades ago before clouds caught on. I figure if a legal or medical practice saw value in LLMs it wouldn’t be a big deal to shove 50k into a closet

With M3 Max with 64GB of unified ram you can code with a local LLM, so the bar is much lower

Sure, but now double the team size. Double it again.

Suddenly that $40k is quite reasonable because you’ll never pay another dollar for st least 2-3 years.

It's not. I've got a single one of those 512GB machines and it's pretty damn impressive for a local model.

This would be an absolute game changer for me. I am dictating this text now on a local model and I think this is the way to go. I want to have everything locally. I'm not opposed to AI in general or LLMs in general, but I think that sending everything over the pond is a no-go. And even if it were European, I still wouldn't want to send everything to some data center and so on. So I think this is a good, it would be a good development and I think I would even buy an Apple device for the first time since the iPod just for that.

Could be, but it likely won't be able to support the massive context window required for performance on par with sonnet 4.6

This is typically true.

And while it is stupid slow, you can run models of hard drive or swap space. You wouldn’t do it normally, but it can be done to check an answer in one model versus another.

Tokens per second is abysmal no matter how much ram you have

48 GB MacBook Pro. All of the models I've tried have been slow and also offered terrible results.

What models are you using? I’ve found that SOTA Claudes outperform even gpt-5.2 so hard on this that it’s cheaper to just use Sonnet because num output tokens to solve problem is so much lower that TCO is lower. I’m in SF where home power is 54¢/kWh.

Sonnet is so fast too. GPT-5.2 needs reasoning tuned up to get tool calling reliable and Qwen3 Coder Next wasn’t close. I haven’t tried Qwen3.5-A3B. Hearing rave reviews though.

If you’re using successfully some model knowing that alone is very helpful to me.

Yes