580 points by linolevan 10 days ago | 569 comments | View on ycombinator
pen2l 10 days ago |
simonw 9 days ago |
There's a name I haven't heard in a long time! Claris (always an Apple subsidiary, since being founded in 1987) renamed themselves to FileMaker in 1998, but apparently they rebranded back to Claris in 2019.
Looks like they've mostly just released annual upgrades to FileMaker for the past decade, but they did add MCP to it last year: https://www.claris.com/blog/2025/why-mcp-matters-for-claris-...
jph 9 days ago |
If/when Anthropic changes to pure API pricing, or for API-heavy projects, that's when I'd switch to more local models. Of course there are tradeoffs for speed, quality, upgradeability, etc.
I currently run a Mac with 128GB and qwen3.8:27b-mlx. It hits the heat limit of the Mac when working on a 200k LOC codebase for security auditing and hardening for many hours at a time. This isn't as strong/fast as Sonnet, to be sure, yet the cost is only $6K one-time plus the usual electricity, maintenance time, etc.
thibsrn 9 days ago |
iantpe 9 days ago |
Jev allows for numerous small judgments: Is this email important? Which program should handle this request? Is this operation risky? There's no need for large LLMs to slowly generate long paragraphs of text; all you need is a fast, structured result that returns the message.
Having a local Jev-like model in the operating system for quick decision-making, and then calling the larger model when deeper thinking is needed, would be very useful.
gehsty 9 days ago |
I am super interested to see what the Apple silicon team can deliver when their full attention is turned to local LLM acceleration.
jedbrooke 9 days ago |
This seems like the main way it would differentiate itself over existing solutions like LMStudio etc.
jwr 9 days ago |
apparent 9 days ago |
If all of this were easy, I would happily invest in new dedicated hardware to run it. This could be a full-blown Mac or it could be a souped up HomePod-type device, loaded with RAM. Better yet, make it a revitalized Matter-enabled Airport!
gizmodo59 9 days ago |
KolibriFly 9 days ago |
_pdp_ 9 days ago |
mgiampapa 10 days ago |
crossroadsguy 9 days ago |
Running local models is already extremely easy.
I have a suspicion this app will be a way to add a too many gigabytes to the mac and of course like the Chess.app there will be no way to get rid of it. There are excellent cli apps/GUI apps like this https://github.com/ddalcu/mlx-serve - they are both cli and gui – and even its gui surprisingly nimble (I use this, but I am not related to the project). I am yet to try this https://github.com/ggml-org/Llama-macOS but I've seen only good reviews of it.
I also do not think Apple is doing it for the users who won't explore around. I can't wait to get off this operating system. Next time a friend travels to the continent I will explore getting a Framework laptop via them.
MBCook 10 days ago |
They desperately need to fix that.
brainless 9 days ago |
LLMs with <30B parameter models seem like the sweet spot. I would rather focus on multiple tiny LLMs that are tuned to specific tasks (SQL queries, finance/accounting, backend/frontend dev, etc.).
For larger models, a $10-40 ish Neuralwatt/Opencode Go or any similar subscription goes so far for the average user that it is ridiculous. We are still in the "youth" era of agents. There are many patterns that work well with smaller LLMs. Or with a big-small LLM combination.
My context:
I own the tiny 16GB M4 Mac Mini and I use LLMs (coding agents) to build software and a few of my products use LLMs directly. Full-time user of LLMs, do not read or write code manually. I run the tiny Qwen series (<10B params) sometimes but a couple $20 subscriptions (Claude, Neuralwatt) take care of my full-time agent usage.
dwaite 8 days ago |
So this is interesting, but it will likely be an independent product rather than part of the core operating system.
api 9 days ago |
Even better would be a peer to peer model hosting hardware pooling system but that’s probably too much to ask and would expose Apple to liability issues in some jurisdictions.
If Apple were willing to eat some margin on RAM they could use the present RAM bubble to gain ground in the hardware market too. Financially you could call it buying market share.
mark_l_watson 9 days ago |
I think it is a great joy to run most things locally, and still occasionally use the best commercial models when local will not cut it.
quaddoggy 9 days ago |
ontouchstart 9 days ago |
In my case it reached the recursive self improvement stage a few weeks ago. It feels like the early days of personal computing in the era of DOS and Apple II.
The hardware is already there. The only limit is product imagination.
kenferry 9 days ago |
Claris?? Ok, this sounds like it's just someone's personal project. Something like this that was actually going to ship would be in a different org.
liuliu 9 days ago |
throwaway_new_1 9 days ago |
nkotov 9 days ago |
pentakkusu 9 days ago |
I use oMLX btw, on 32GB URAM, running Hermes with Qwen 3.6 @ 128k context window.
I realize I am a smalltimer but for general day to day sensitive agentic stuff, this is the entry point.
caycep 8 days ago |
zf00002 9 days ago |
avazhi 8 days ago |
nier 9 days ago |
azuanrb 9 days ago |
It’s the “year of the Linux desktop” meme all over again. Any day now.
- From a happy iPhone Duo user
D13Fd 9 days ago |
ourcat 7 days ago |
rcarmo 9 days ago |
w10-1 10 days ago |
glassresearch 7 days ago |
chews 9 days ago |
fridder 9 days ago |
ggcr 9 days ago |
lenerdenator 9 days ago |
DerDerDaIst 9 days ago |
so you can control and monitor what the whole setup is doing inside and outside the box.
nxobject 9 days ago |
wewewedxfgdf 9 days ago |
wingi 9 days ago |
amelius 9 days ago |
sleight42 9 days ago |
... Looks like I picked the wrong week to buy parts for a linux-based inference box.
axnli 9 days ago |
heyeddi 9 days ago |
dcdevito 8 days ago |
ankur_misra 9 days ago |
geberele 8 days ago |
ravivarmat 9 days ago |
simli123 9 days ago |
ilkerguldali 10 days ago |
tonymet 9 days ago |
rickdg 9 days ago |
q4y2u35uk 10 days ago |
myphpgothacked 9 days ago |
Distillation works: we can get models leaner, have better performance with lesser and lesser parameters, more efficient, running locally. Apple gets this and we'll see the result with M7 Max/ultra chips and I reckon this will be one of the titular apps when M7 line of chips are introduced.
I guess it explains the haste Anthropic and OpenAI are in to IPO, cash out and leave the the retail investor holding the bag.