> not even considering business security.

I suspect personal privacy and need to run AI workflows to handle the litany of administration tasks of a household will be what result in regular need for local AI.

Apple is already out front with this on a personal, individual level, but they are not obviously headed toward multiuser/family-level ~biz admin with a persistent server running local LLM.

"I am not sure how many people will run AI models locally. It still seems like a niche application to me. However, it will make decent machines to play video games..."

This is the 2026 edition of Ken Olsen: "There is no reason anyone would want a computer in their home"

He’s just a braggart. When you see something like this in somebody’s personal bio on social media, it’s basically a banner that means “take everything I say in the context of me promoting myself.”

Qwen 3.6 is far ahead of Gemma for most (but not all) things. I've deployed it out across a number of M5 MacBooks and it's genuinely useful for many tasks. It won't replace an Opus or current gen Sonnet sized model but it's still amazingly good for its size and probably as good as or just a bit before Sonnet 4 era. Far more reliable for tool calling, coding, agentic tasks and faster than the Gemma models especially with MTP.

I also don't get why this twitter user is linked here, versus all the news articles about this new hardware that have been everywhere over the past number of days.

The HN crowd is, by and large, not the target audience for his self promotion. I guarantee there is one and this is more or less effective.

> you may run some models locally if only from a cost perspective

I have a hard time believing running a model on a laptop will be cheaper than running it in a datacenter. Why wouldn't economies of scale apply here as with every other computation?

> this guy puts this everywhere, gives me probably the inverse of what he is marketing for.

Do you think he's in mensa too?

The security aspect is the main driver why I’m seeing so many businesses investing in local hardware. They know the models aren’t as good (caveat that they also can’t run Chinese models) and that’s ok. Places that really care about security and data governance already aren’t on the bleeding edge. They wait for the nice stable lts version, they lock down dev machines in frustrating ways and have lots of IT admin layers.

But they also want to taste the sweet fruit of AI so the only way to do this that a CISO will approve is on local air gapped hardware. It’s a niche but still a billion dollar niche.

> However, it will make decent machines to play video games."

Where you will need games to be rewritten for ARM to get full performance, just like on Apple's M series chips.

Maybe they just mean from a "it can run a lot of DLSS" perspective.

DeepSeek Flash v4 is the leading local AI on 128GB machines, and DS4 is still in preview (training not finished), no?

Especially on Dwarfstar.

128GB seems the sweet spot for local models. I can program and install most GitHub projects with opencode and QWEN 32b with mtp.

anyone whose addicted to token theoughput is losing the operational knowledge and offline capabilities.

if you arent moving to the AMD 395 or MACs then youre hitching aride on the expensive calory ride

> "Ranked in the top 2% of scientists globally (Stanford/Elsevier 2025) and among GitHub's top 1000 developers"

This made me laugh. I can only image how insufferable this person is to deal with.

I hope a family-level AI appliance is a thing later. Local non-cloud assistant that lives in the house, families interact via voice or phones or whatever. Knows the contextual family stuff you need, etc.

Lots of people are already running AI locally. They are the people buying up all the consumer-grade nvidea gpus. What are they doing with them? Well, the same things people with home media or email servers are doing: stuff they dont want to share with the general public.

I think the local-model use case is going to become less niche pretty quickly if the models keep getting smaller and more capable. Even if most people do not care about privacy or offline use, the cost argument is pretty strong

> "Ranked in the top 2% of scientists globally (Stanford/Elsevier 2025) and among GitHub's top 1000 developers" - side note but this guy puts this everywhere, gives me probably the inverse of what he is marketing for.

Lol yeah seriously, that stinks "I ask AI to generate a huge amount of bullshit and upload it to pad irrelevant stats".

Absolute loser.