Discussion summary
Many discuss the shift towards local AI, emphasizing improved hardware and tools like QMD. Some highlight challenges such as UX, scope limitations, and hardware constraints.
What the discussion says
- Local AI could reduce reliance on cloud services as hardware improves.
- Tools like QMD facilitate local model deployment.
- Challenges include UX, hardware limitations, and model scope.
- Some see local AI as democratizing access.
- Concerns about hardware security and access restrictions.
“A lot of AI aspects probably don’t need to be permanent cloud services.”
“More important is democratizing AI for the common masses.”
Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- The example in the post confirms my theory that for local models to succeed they need to be "good enough", not big enough that they can compete with frontier models.
They need to be able to do a small task well and they need to be able to run reasonably on consumer-class devices. Even better if they can run on mobile phones.
In my experiments with local LLMs I noticed that while increasing the size of the model is nice the real thing that turns a barely useless model into something useful is the ability to use tools. Giving my models the ability to search the web and fetch web pages did way more to solve hallucinations than getting a bigger model. And it doesn't have a training cutoff. Sure, the bigger model is probably better at using tools but I often find the smaller models to be good enough.
by wrxd - It seems like everybody is focused on "LLM"s, a.k.a Large Language Models. One interesting addition to that is fine-tuned- small parameter, distilled, context-dependent small language models that:
1- Do a particular task with great capability (due to its constrained, limited scope) 2- Do it in such a way, it integrates gracefully in your workflow without ever requiring you to know you are using an LM.
There is a difference between outsourcing your workflow to AI and actually utilizing it.
Check this: https://www.distillabs.ai/blog/we-benchmarked-12-small-langu...
by gkcnlr - For the mainstream audience, the sentiment around local ai today is the same that they had around open source a few decades ago. For a few products, some paid solutions were so much more advanced that open source were very often completely overlooked. Why bother ? And the like. Then we had captive SaaS and other plateforms and now it's obviously wrong for most of us.
The dependency we have with anthropic and openai for coding for instance is insane. Most accept it because either they don't care, or they just hope chinese will never stop open weights. The business model of open weights is very new, include some power play between countries and labs, and move an absurd amount of money without any concrete oversight from most people.
It's a very dangerous gamble. Today incredible value is available for nearly everyone. But it may stop without any warning, for reason outside our control.
by TheJCDenton - Cool, well let me know when Opus 4.5 level performance is available locally, at speeds that serve everyday use, and 100% I'm right there with you.
Until then, I'm going to keep sending my JSON to the server farm in Virginia because it's the only place that can serve me a model that actually works for my uses.
- I'm literally working on an iOS app right now that needs to infer some input fields from free text typed by the user. Now to take into consideration typos, unstructured text (pricing, dates .. etc), I was pondering a cloud LLM or a basic local parser or even a local on-device LLM (ANE for 15+ devices and a different on-device LLM for the older models)
For the different on-device LLM, I literally went to HuggingFace and filtered by the smallest available models that can do the job, and Granite-4.0-h-1b works just fine, it corrects typos, infers dates, currencies all fields I need.
And it got me thinking how my first reflex was to rely on a cloud LLM which is waaay overkill for my need. Granted, an on-device LLM will need to be loaded on the devices on install or downloaded after the fact (which adds latency when the user needs it for the first time) but still, it's a better tradeoff than a cloud LLM.
I decided on a basic parser, and so far it seems to work fine. granted, it struggles with some words, but I just need to finetune it to have as much coverage as possible in terms of typos without triggering false positives.
A lot of developers have that reflex too and go along with it and then just pass the API costs to the customer. I could have gone that route too but turned out I don't even need an LLM for my usecase.
by chakintosh - Here's some things you can do right now with local models on a consumer device:
- text-to-speech - speech-to-text - dictionary - encyclopedia - help troubleshooting errors - generate common recipes and nutritional facts - proofread emails, blog posts - search a large trove of documents, find information, summarize it (RAG) - manipulate your terminal/browser/etc - analyze a picture or video - generate a picture or video - generate PDFs, documents, etc (code exec) - simple programming - financial analysis/planning - math and science analysis - find simple first aid/medical information - "rubber ducking" but the duck talks back
A quarter of those don't need more than a gig of RAM, the rest benefit from more RAM. Technically you don't even need a GPU, it just makes it faster. I do half that stuff on my laptop with local models every day.
That said, it really doesn't need to be local. I like the idea that I can do all that stuff offline if I'm traveling, but I usually have cell service, and the total tokens is pretty cheap (like $2/month for all my non-coding AI use).
by 0xbadcafebee - I feel like lots of people here are just commenting on the headline.
This isn't about the local models you're running on your old gaming rig, or the tesla p40 rig you build for local llm's.
This is about code leveraging the local resources where the code is running for it's AI needs. Rather than making an API call to an external AI service, the code leverages the AI capabilities built into the hardware it runs on. With modern Apple, Intel, and AMD silicon all shipping dedicated AI acceleration, this is the where IMO the focus should be heading.
How many Flops or whatever can your phone do? I bet it's enough to paint the walls of your living room, or draw a pretty good pelican on a bike.
by Akuehne - They will be, and that moment is not that far off. We've got the progression in place already: first, large data centers could have performant LLMs, we are now firmly in "a bunch of servers with a couple of H100s each" territory, slowly going into "128 GB VRAM on a MacBook Pro or a Strix Halo". Within the next year, the pattern of "expensive remote LLM for planning, local slow-but-faster-than-human LLM for execution" will become the norm for companies, slowly moving to "using local LLM for everything is good enough". And then we'll have the equilibrium we already have with the "classic cloud": you either self-host or pay for flexibility and speed. The question will be: how much of the current compute capacity craze will local hosting give the kiss of death to and what that means for the market.by pronik