The big question is whether Apple can keep shipping new models constantly.
AFAIK the current model is on par with with Qwen-3-4B, which is from a year ago [0]. There's a big leap going from last year Qwen-3-4B to Qwen-3.5-4B or to Gemma 4.
Apple model is nice since you don't need to download anything else, but I'd rather use the latest model than to use a model from a year ago.
I’m not sure why that’s a question, it’s just a downloaded file. You can even watch it download separately when you enable Apple Intelligence (it’s not tied to OS updates from what I can tell).
Of course I imagine Apple is not going to be the fastest mover in this regard. I’m not even sure they believe the product will be widely impactful anymore and may keep it relegated to a small list of popular use cases like photo touch ups and quick questions to Siri. For me the most useful parts of Apple’s AI don’t even require me to enable Apple Intelligence.
convexly 7 hours ago [-]
I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant. The amount of articles that come out about accidents happening because of people handing too much context to cloud models the more self reinforcing this will become.
cousin_it 5 hours ago [-]
It's only half of the solution though. If the models are trained in a closed way, they can prioritize values encoded during training even if that's not what you want (example: ask the open Chinese models about Tiananmen). It's not beyond imagining that these models would e.g. try to send your data to authorities or advertisers when their training says so, even if you run them locally.
So the full solution would be models trained in an open verifiable way and running locally.
wrxd 3 hours ago [-]
The model is only generating tokens without touching the network at all, right? How would it send data away?
procaryote 3 hours ago [-]
Theoretically, by taking the opportunity to inject an exfiltration mechanism if you ask it to write code for you
kg 2 hours ago [-]
Lots of people I know run models in "yolo" mode or the equivalent as well, which means it could just invoke curl or telnet to exfiltrate data.
Xenoamorphous 1 hours ago [-]
> I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant.
In HN circles perhaps. Average Joes don’t care.
hombre_fatal 4 hours ago [-]
Another angle is when you're passing untrusted content to the AI service, e.g. anything from using it to crawl websites to spam-detection on new forum user posts.
You can trigger the the service's ToS violation or worse, get tipped off to law enforcement for something you didn't even write.
lukewarm707 6 hours ago [-]
local is best for privacy, but i personally think you don't need to go local.
anthropic, google, openai etc, decided that their consumer ai plans would not be private. partly to collect training data, the other half to employ moderators to review user activity for safety.
we trust that human moderators will not review and flag our icloud docs, onedrive or gmail, or aggregate such documents into training data for llms. it became the norm that an llm is somehow not private. it became a norm that you can't opt out of training, even on paid plans (see meta and google); or if you can opt out of training, you can't opt out of moderation.
cloud models with a zero retention privacy policy are private enough for almost everyone, the subscriptions, google search, ai search engines are either 'buying' your digital life or covering themselves for legal reasons.
you can and should have private cloud services, and if legal agreement is not enough, cryptographic attestation is already used in compute, with AWS nitro enclaves and other providers.
inetknght 6 hours ago [-]
> i personally think you don't need to go local.
I personally think everyone should default to using local resources. Cloud resources should only be used for expansion and be relatively bursty rather than the default.
mark_l_watson 5 hours ago [-]
For about two years I experimented with writing local apps using local LLMs, but I often had to blend in a commercial web search API to make my little experiments useful.
Whyachi 3 hours ago [-]
[dead]
mark_l_watson 5 hours ago [-]
I pay $13/month for Proton’s Lumo+ private chat LLM that contains an excellent built-in web search tool. I use it for everything non-technical, even just simple searching for local businesses, etc.
As an enthusiastic reader of books like Privacy is Power and Surveillance Capitalism, it feels good to have a private tool that is ready at hand.
djl0 5 hours ago [-]
do you have any provider recommendations? I've experimented with this on runpod serverless, but I've been meaning to dig deeper before I feel comfortable with personal data.
I saw a service named Phala, which claims to be actually no-knowledge to server side (I think). It was significantly more expensive, but interesting to see it's out there. My thought was escaping the data-collection-hungry consumer models was a big win.
ge96 5 hours ago [-]
The other thing, is encrypted inferencing a thing/service currently? I want to run my own models locally just because if I'm going to be chatting to it about my day to day life why send it to a server in plaintext.
lukewarm707 5 hours ago [-]
encrypted inferencing, meaning homomorphic encryption: no, it's not solved.
cryptographic confirmation of zero knowledge: yes.
the latter, based on trust in the hardware manufacturer and their root ca. so, encrypted if you trust intel/nvidia to sign it.
there are a few services, phala, tinfoil, near ai, redpill is an aggregator of those
aswanson 6 hours ago [-]
That's the way things have to go. Business risk is too high having everything ran over exposed networks.
lukewarm707 6 hours ago [-]
what i say about this, is that an llm is just a big file, there is nothing 'not private' about it.
if you are happy with off-prem then the llm is ok too, if you need on-prem this is when you will need local.
zahlman 6 hours ago [-]
> an llm is just a big file, there is nothing 'not private' about it.
The private thing is the prompt.
But also, a local LLM opens up the possibility of agentic workflows that don't have to touch the Internet.
gherkinnn 6 hours ago [-]
Now this is a development I like.
With the Claude bug, or so it is known, burning through tokens at record speed, I gave alternative models a try and they're mostly ... interchangeable. I don't know how easy switching and low brand loyalty and fast markets will play out. I hope that local LLMs will become very viable very soon.
naravara 6 hours ago [-]
Yeah I don’t think the models are meaningfully differentiated outside of very specific edge cases. I suspect this was the thinking behind OpenAI and Facebook and all trying to lean hard into presenting their chatbots as friends and romantic partners. If they can’t maintain a technical moat they can try to cultivate an emotional one.
g-mork 3 hours ago [-]
Saw a comment here yesterday referencing the Attention Is All You Need paper title in a tongue in cheek way. Kinda fun to imagine the friend/romance angle is just a bunch of socially awkward folk at OpenAI misinterpreting the original paper
brians 7 hours ago [-]
I’ve seen several projects like this that offer a network server with access to these Apple models. The danger is when they expose that, even on a loop port, to every other application on your system, including the browser. Random webpages are now shipping with JavaScript that will post to that port. Same-origin restrictions will stop data flow back to the webpage, but that doesn’t stop them from issuing commands to make changes.
Some such projects use CORS to allow read back as well. I haven’t read Apfel’s code yet, but I’m registering the experiment before performing it.
brians 7 hours ago [-]
They offer it as an option but default it to false! This is still a --footgun option but it’s the least unsafe version I’ve seen yet! Well done, Apfel authors.
I think any browser will allow it but not allow data read back.
btown 7 hours ago [-]
FWIW this was the status quo (webpage could ping arbitrary ports but not read data, even with CORS protections) - but it is changing.
This is partially in response to https://localmess.github.io/ where Meta and Yandex pixel JS in websites would ping a localhost server run by their Android apps as a workaround to third-party cookie limits.
So things are getting better! But there was a scarily long time where a rogue JS script could try to blindly poke at localhost servers with crafty payloads, hoping to find a common vulnerability and gain RCE or trigger exfiltration of data via other channels. I wouldn't be surprised if this had been used in the wild.
airza 7 hours ago [-]
There is a CORS preflight check for POST requests that don't use form-encoding. It would be somewhat surprising if these weren't using JSON (though it wouldn't be that surprising if they were parsing submitted JSON instead of actually checking the MIME-type which would probably be bad anwyay)
mememememememo 7 hours ago [-]
Isn't there a CORS preflight check for this? In most cases. I guess you could fashion an OG form to post form fields. But openai is probably a JSON body only.
The default scenario should be secure. If the local site sends permissive CORS headers bets may be off. I would need to check but https->http may be a blocker too even in that case. Unless the attack site is http.
robotswantdata 7 hours ago [-]
Keep seeing similar mistakes with vibe coded AI & MCP projects. Even experienced engineers seem oblivious to this attack vector
snarkyturtle 6 hours ago [-]
Noting that there's an option to require a Bearer token to the API
Multiplayer 5 hours ago [-]
Started using this earlier this week. I built a backtesting benchmark tool to compare a mix of frontier and open-source models on a fairly heavy data analysis workflow I’d been running in the cloud.
The task is basically predicting pricing and costs.
Apple’s model came out on top—best accuracy in 6 out of 10 cases in the backtest. That surprised me.
It also looks like it might be fast enough to take over the whole job. If I ran this on Sonnet, we’re talking thousands per month. With DeepSeek, it’s more like hundreds.
So far, the other local models I’ve tried on my 64GB M4 Max Studio haven’t been viable - either far too slow or not accurate enough. That said, I haven’t tested a huge range yet.
frontsideair 4 hours ago [-]
> Apple locked it behind Siri. apfel sets it free
This doesn't feel truthful, it sounds like this tool is a hack that unlocks something. If I understand it correctly, it's using the same FoundationModels framework that powers Apple Intelligence, but for CLI and OpenAI compatible REST endpoint. Which is fine, just the marketing goes hard a bit.
> Runs on Neural Engine
Also unsure if this runs on ANE, when I tried Apple Intelligence I saw that it ran on the GPU (Metal).
reaperducer 4 hours ago [-]
This doesn't feel…
Also unsure…
Thank you for sharing your feelings and uncertainty.
Perhaps resist the urge to post until you have something to contribute.
halJordan 2 minutes ago [-]
Using soft or unsure wording doesn't obviate the factualness of the contribution. The op is correct on both accounts- it's ok to be unsure when putting it forward.
You on the other hand contributed literally nothing to the topic
> Also unsure if this runs on ANE, when I tried Apple Intelligence I saw that it ran on the GPU (Metal).
They added something of some substance here.
Your post expressing your feelings did not.
3 hours ago [-]
gurjeet 4 hours ago [-]
Thank you for making it open source!
Submitted a PR to prevent its installation on macos versions older than Tahoe(26), since I was able to install it on my older macos 15, but it aborted on execution.
I find the branding to be a little odd. Like, it should be a github page with a README that says "here's how to use this." Like, the full explanation of this project is right there in the HN title: "The free AI already on your Mac."
I guess LLMs have made it too simple to instantly build startup landing page slop, which causes this? Like, do we need to see the github star count chart? Do we need all the buzzwords and stuff? You'd think this was a startup trying to get a billion dollar evaluation. It feels disingenuous.
Maybe I'm just being a hater.
ronb1964 3 hours ago [-]
I'm a Linux user who wanted exactly this but for Linux — so I ended up building it myself. It's called TalkType, it runs Whisper locally for offline speech-to-text. The privacy angle was a big reason I went local from the start — I didn't want my voice being sent to anyone's server. Nice to see the same idea getting traction on Mac.
lewisjoe 4 hours ago [-]
Tempted to write a grammarly-like underline engine that flags writing mistakes across all apps and browser. Fully private grammarly alternative without even bundling an LLM!
malshe 2 hours ago [-]
That's a great idea. I would be very interested in using it of someone builds it.
khalic 8 hours ago [-]
AFM models are very impressive, but they’re not made for conversation, so keep your expectations down in chat mode.
donmb 6 hours ago [-]
Local AIs are the future in times of limited resources. This could be the beginning of something big. I like that Apple opens up like this. Hopefully more to come.
enjoyitasus 5 hours ago [-]
completely agree.
Barbing 6 hours ago [-]
Just discovered iOS shortcuts has a native action called “use model” that lets you use local, Apple cloud, or ChatGPT— before that I would have agreed with the author about being locked behind Siri (natively)
kangraemin 6 hours ago [-]
4,096 token context window is pretty limiting. That's roughly 3,000 words — fine for "summarize this paragraph" but not enough for anything that needs real context. Still, zero cost and fully local is hard to beat for quick throwaway tasks. Does it handle streaming or is it request-response only?
xandrius 3 hours ago [-]
Try it and see
Phemist 5 hours ago [-]
Nice! The example should imo say
apfel -o json "Translate to German: apple" | jq .content
Unfortunately, I found the small context window makes the utility pretty limited.
troyvit 5 hours ago [-]
Yeah I think you hit on the head a good way to use it though. I'm not on MacOS but KDE has a little tool called krunner[1] that lets you perform simple tasks from a small pop-up on your desktop. It would be cool if I could do slightly agentic things from there with a local model like ask what the capital of Austria is, or what's the current exchange rate between two currencies.
It's really handy for quick things like "what's the capital of country x" but for coding, I feel that it is severely limited. With such a small context it's (currently) not great for complicated things.
VanTodi 6 hours ago [-]
Just a small thing about the website: your examples shift all the elements below it on mobile when changing, making it jump randomly when trying to read.
rbbydotdev 6 hours ago [-]
Would really love to see a web api standard for on device llms. This could get us closer. Some in-browser language model usage could be very powerful. In the interim maybe a little protocol spec + a discovery protocol used with browser plugins, web apps could detect and interface with on-device llms making it universally available.
For those who don't know, 'Apfel' is the German word for Apple.
gherkinnn 6 hours ago [-]
And for those who did know that and want to know more, the shift from apple - apfel and water -> wasser happened during the High German consonant shift.
As an experiment I built a prototype chatbot app that uses the built-in LLM. It’s got a small context window, but is surprisingly capable and has tool-calling support. Without too much effort I was able to get it to fetch weather data, fetch and summarise emails, read and write reminders and calendar events.
swiftcoder 8 hours ago [-]
Anyone tried using this as a sub-agent for a more capable model like Claude/Codex?
LatencyKills 8 hours ago [-]
The combined (input/output) context window length is 4K. Claude would blow through that even when trying to read and summarize a small file.
knocte 3 hours ago [-]
With a small/minimalistic harness like Pi maybe it works well?
khalic 7 hours ago [-]
If you’re looking into small models for tiny local tasks, you should try Qwen coder 0,5B. It’s more of an experiment, but it can output decent functions given the right context instructions.
xenophonf 6 hours ago [-]
> [Qwen coder 0,5B] can output decent functions given the right context instructions
Can you share a working example?
khalic 6 hours ago [-]
So… a prompt? I’m not on my laptop but I hooked it to cmp.nvim, gave it a short situational prompt, +- 10 lines, and started typing. Not anywhere near usable but with a little effort you can get something ok for repetitive tasks. Maybe something like spotting one specific code smell pattern. The advantage is the ridiculous T/s you get
coredog64 3 hours ago [-]
I was thinking about the other way: Could you use this in front of Claude to summarize inputs and so reduce your token counts?
franze 8 hours ago [-]
project started with
trying to run openclaw with it in ultra token saving mode, did totally not work.
great for shell scripts though (my major use case now)
divan 4 hours ago [-]
What's the easiest way to use it with on-device voice model for voice chat?
Thanks, tried it, but it's crashes on clicking the microphone icon. Default `make install` for some reason tries to install it to /usr, I changed that and after torturing more mature coding LLMs for 20 minutes, made it running with mic/sound.
The mic button requires clicking to transcribe and start listening again, and default voice is low-quality (I assume it can be configured).
In general I'm looking for a way to try the on-device hands-free voice mode.
Does the local LLM have access to personal information from the Apple account associated with the logged-in user? Maybe through a RAG pipeline or similar? Just curious if there are any risks associated with exposing this in a way that could be exploited via CORS or through another rogue app querying it locally.
franze 6 hours ago [-]
no. the on device foundationmodels framework that apfel uses does not have access to personal information from the apple account. the model is a bare language model with no built in personal data access.
apple does have an on device rag pipeline called the semantic index that feeds personal data like contacts emails calendar and photos into the model context but this is only available to apples own first party features like siri and system summaries.
it is not exposed through the foundationmodels api.
6 hours ago [-]
Oras 7 hours ago [-]
I like the idea and the clarity to explain the usage, my question would be: what kind of tasks it would be useful for?
khalic 7 hours ago [-]
Making a sentence out of a json
mark_l_watson 6 hours ago [-]
I have been using Apple’s built-in system LLM model for the last 7 or 8 months. I like the feature that if it needs to, it occasionally uses a more powerful secure private cloud model. I also write my own app to wrap it.
pbronez 6 hours ago [-]
Digging into this, found Apple’s release notes for the Foundation Model Service
The ATP episode where he talked about this was incredibly fascinating. Marco is such a role model to me - he has a complete immunity to fads and trends, and just does things the way he wants to. He adopts the 'new and cool' things only when they have a real benefit.
gigatexal 2 hours ago [-]
I largely subscribe to the use boring tech ethos ... but php? come on man.
and yet... successful people have used it to build really successful things: Facebook, Tumblr (I think), the things Marco's been involved with.
I just dunno outside of meta should we really be pushing php with all its flaws? or is it still flawed and I need to update my priors?
bombcar 20 minutes ago [-]
There’s something major to be said for going to war with the tools you have.
And living with decisions made 15 years ago may be much more successful than trying to change horses mid-stream.
gigatexal 3 hours ago [-]
Yeah heard him talk about that. 48 or so 16GB m4 Mac minis. Insane. The Beowulf lives
FinnKuhn 7 hours ago [-]
For small tasks this seems perfect. However it being limited to English from what I can tell is quite a downsite for me.
Just use the language you want when prompting it, like other LLMs?
% apfel "Gib mir ein Rezept für Currywurst."
Natürlich! Hier ist ein einfaches Rezept für Currywurst:
### Zutaten:
- **Für die Würste:**
- 500 g Bratwürste (z. B. Frankfurter Würste)
(note: clipped most of the reply, since I assume most of us here don't actually need an LLM-generated recipe)
thenthenthen 8 hours ago [-]
The vision models and OCR are SUPER
deadfox 3 hours ago [-]
This is cool!
yalogin 3 hours ago [-]
This is great. A few questions come to mind, I need to go look up. Is the model an OpenAI one or home grown for Apple. And can I still use it if Siri is disabled?
contingencies 2 hours ago [-]
1. Hugely non-deterministic: repeat queries give vastly different responses. 2. Often returns incorrect and inconsistent results even for mathematical queries. 3. Often the responses include unwanted highlighting or presentation markup. 4. Defaults to German decimal notation.
contingencies 3 hours ago [-]
On a similar bent, I recently discovered Handy (cross-platform) which is very well implemented local voice input: https://handy.computer/ ... serious finger saver and ideal for LLM conversations
p1anecrazy 9 hours ago [-]
Really like demo cli tools description. Are they limited by the context window as well? What’s your experience with log file sizes?
franze 8 hours ago [-]
the 2 hard limits of Appel Intelligence Foundation Model and therefor apfel is the 4k token context window and the super hard guardrails (the model prefers to tell you nothing before it tells you something wrong ie ask it to describe a color)
parsing logfiles line by line, sure
parsing a whole logfile, well it must be tiny, logfile hardly ever are
reaperducer 4 hours ago [-]
the model prefers to tell you nothing before it tells you something wrong
If all LLMs did this, people would trust them more.
furyofantares 4 hours ago [-]
Looks like a nice wrapper around the APIs. Extremely oversold landing page, very marketing heavy for what it is. You can actually make nice looking landing pages that are about 10% the size of this and more straightforward, rather than some mimicry of a SaaS that's trying desperately to sell you something. Makes it easier for you to review the content for factuality too, and heck you couldn't even take ownership of some of the voice.
Hard to know what to do with this. I'm interested in the project and know others who would be, but I feel like shit after being slopped on by a landing page and I don't wish to slop on my friends by sharing it with them. I suppose the github link is indeed significantly better, I'll share that.
xandrius 3 hours ago [-]
It's absolutely free and open source, no need to bash it like this.
furyofantares 2 hours ago [-]
I certainly don't feel entitled to anybody's effort, and I appreciate the project itself!
It's just these flashy LLM-generated webpages are really misleading.
It's filled with attention-grabbing LLM-filler. It presents itself as high-effort content, but in reality is unclear if it's accurate, unclear how much the author even put into READING the content they're asking me to read, and overall just really unclear what parts of the page are important to the author and what are just stuff the LLM inserted into a marketing card to make it look like a SaaS sales pitch.
wrxd 2 hours ago [-]
If you dislike the slop on the website so much you might also not like GitHub that much. It shows this software has been heavily co-written by Claude code
furyofantares 2 hours ago [-]
I'm aware of that! That's fine with me.
elcritch 8 hours ago [-]
Any know if these only installed on Tahoe? I'm running Sequoia still and get an error about model not found.
HelloUsername 8 hours ago [-]
> Apple Silicon Mac, macOS 26 Tahoe or newer, Apple Intelligence enabled
jonpurdy 6 hours ago [-]
Yes, the model ships with Tahoe, not previous versions.
I too would love to try this for simple prompts but won’t be updating past Sequoia for the foreseeable future.
als0 5 hours ago [-]
Same. What a disaster Tahoe is.
witnessme 3 hours ago [-]
Interesting. How does this foundational model compares with other LLMs?
joriskok1 6 hours ago [-]
How much storage does it take up?
franze 5 hours ago [-]
4mb download, after install about 15mb, model is already on your mac with mac os x tahoe
reaperducer 4 hours ago [-]
apfel "How many shopping days until Christmas?"
To determine how many shopping days until Christmas, you'll need to know the current date and the date of Christmas. Christmas is on December 25th, so you can subtract the current date from this date to find the number of shopping days. If you provide the current date, I can help you calculate that.
apfel "How many shopping days until Christmas? Today is April 3rd."
To calculate the number of shopping days until Christmas, we first need to determine the date of Christmas this year.
Christmas in 2023 is on December 25th.
Starting from April 3rd, we calculate the days:
1. April: 30 days (from April 3rd to April 30th)
2. May: 31 days
3. June: 30 days
4. July: 31 days
5. August: 31 days
6. September: 30 days
7. October: 31 days
8. November: 30 days
Adding these up gives us:
30 + 31 + 30 + 31 + 31 + 30 + 31 + 30 = 252 days
Christmas is on December 25th, so we subtract 252 days from today, April 3rd:
252 - 252 = 0 days
So, there are 0 shopping days left until Christmas, but since Christmas is already past, there are no shopping days left.
Yep, feels like Siri.
CharlesW 11 minutes ago [-]
This isn't a good test for any model since LLMs can't math (even though frontier models can sometimes correctly simulate mathing), which is why one would always use a tool for this.
6persimmon 56 minutes ago [-]
Almost about to try it until I saw this. If it's Siri the Silly don't even make up for the opportunity cost.
xp84 2 hours ago [-]
Real experience I've had:
"Text Carol bring me a glass of water please"
"I'm sorry, I don't see a 'Carol Bring' in your contacts"
als0 6 hours ago [-]
Is this for Tahoe only? I’m still clutching onto Sequoia
anentropic 5 hours ago [-]
Yeah seems to need Tahoe (I'm on Sequoia):
dyld[71398]: Library not loaded: /System/Library/Frameworks/FoundationModels.framework/Versions/A/FoundationModels
Referenced from: <32818E2F-CB45-3506-A35B-AAF8BDDFFFCE> /opt/homebrew/Cellar/apfel/0.6.25/bin/apfel (built for macOS 26.0 which is newer than running OS)
Reason: tried: '/System/Library/Frameworks/FoundationModels.framework/Versions/A/FoundationModels' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/System/Library/Frameworks/FoundationModels.framework/Versions/A/FoundationModels' (no such file), '/System/Library/Frameworks/FoundationModels.framework/Versions/A/FoundationModels' (no such file, not in dyld cache)
linsomniac 5 hours ago [-]
Yes, it says on that page that it uses Apple Intelligence from Tahoe. I'm also hanging onto Sequoia, though I'm ready to make the leap any time here.
crena 4 hours ago [-]
MacBook Neo forced me to finally make the jump, and it turns out that I, much like the engineers at Apple, don't really care about the spit and finish anymore. Third-party applications handle everything else. Also, I was happy to find that Divvy still runs just fine under Rosetta.
sys_64738 5 hours ago [-]
Tahoe+ only
api 6 hours ago [-]
BoltAI also does this, but a CLI tool is nice.
It’s a nice LLM because it seems fairly decent and it loads instantly and uses the CPU neural engine. The GPU is faster but when I run bigger LLMs on the GPU the normally very cool M series Mac becomes a lap roaster.
It’s a small LLM though. Seems decent but it’s also been safety trained to a somewhat comical degree. It will balk over safety at requests that are in fact quite banal.
walthamstow 6 hours ago [-]
You have to enable Apple Intelligence so that's a hard no from me. I'll stick to LM Studio and gpt-oss/qwen. Very cool project though.
phplovesong 6 hours ago [-]
This is pretty cool. My bet is that we have more LLMs running locally when its possible, either thru "better hardware as default" or some new tech that can run the models on commodity hardware (like apple silicon / equivalent PC setup).
10 hours ago [-]
brtkwr 6 hours ago [-]
[dead]
aiiaro 5 hours ago [-]
[dead]
volume_tech 6 hours ago [-]
[dead]
8 hours ago [-]
Remi_Etien 9 hours ago [-]
[dead]
adettya009 3 hours ago [-]
[dead]
3yr-i-frew-up 6 hours ago [-]
[dead]
devcraft_ai 4 hours ago [-]
[dead]
animanoir 5 hours ago [-]
[dead]
hackerman70000 6 hours ago [-]
[flagged]
skrun_dev 10 hours ago [-]
Notes.app handles big notebooks without choking on storage?
alwinaugustin 6 hours ago [-]
Read Austria as Australia and thought this as an April fool
ramon156 8 hours ago [-]
Cool tool but I don't get why these websites make idiotic claims
A serious project would do the work to be delivered via the native homebrew repository, not a “selfhosted” one.
brtkwr 6 hours ago [-]
Isn't the whole idea of "home brew" to enable hackers and enthusiasts to easily share what they built?
post-it 6 hours ago [-]
Is this you signing up as a packager or
nottorp 6 hours ago [-]
> Starting with macOS 26 (Tahoe), every Apple Silicon Mac includes a language model as part of Apple Intelligence.
So you have to put up with the low contrast buggy UI to use that.
xp84 3 hours ago [-]
> Referenced from: <32818E2F-CB45-3506-A35B-AAF8BDDFFFCE> /opt/homebrew/Cellar/apfel/0.6.25/bin/apfel (built for macOS 26.0 which is newer than running OS)
This actually looks really neat. I'll have to bookmark this for whenever I'm dragged kicking and screaming into the abomination that is "Tahoe."
Rendered at 19:13:10 GMT+0000 (Coordinated Universal Time) with Vercel.
AFAIK the current model is on par with with Qwen-3-4B, which is from a year ago [0]. There's a big leap going from last year Qwen-3-4B to Qwen-3.5-4B or to Gemma 4.
Apple model is nice since you don't need to download anything else, but I'd rather use the latest model than to use a model from a year ago.
https://machinelearning.apple.com/research/apple-foundation-...
Of course I imagine Apple is not going to be the fastest mover in this regard. I’m not even sure they believe the product will be widely impactful anymore and may keep it relegated to a small list of popular use cases like photo touch ups and quick questions to Siri. For me the most useful parts of Apple’s AI don’t even require me to enable Apple Intelligence.
So the full solution would be models trained in an open verifiable way and running locally.
In HN circles perhaps. Average Joes don’t care.
You can trigger the the service's ToS violation or worse, get tipped off to law enforcement for something you didn't even write.
anthropic, google, openai etc, decided that their consumer ai plans would not be private. partly to collect training data, the other half to employ moderators to review user activity for safety.
we trust that human moderators will not review and flag our icloud docs, onedrive or gmail, or aggregate such documents into training data for llms. it became the norm that an llm is somehow not private. it became a norm that you can't opt out of training, even on paid plans (see meta and google); or if you can opt out of training, you can't opt out of moderation.
cloud models with a zero retention privacy policy are private enough for almost everyone, the subscriptions, google search, ai search engines are either 'buying' your digital life or covering themselves for legal reasons.
you can and should have private cloud services, and if legal agreement is not enough, cryptographic attestation is already used in compute, with AWS nitro enclaves and other providers.
I personally think everyone should default to using local resources. Cloud resources should only be used for expansion and be relatively bursty rather than the default.
As an enthusiastic reader of books like Privacy is Power and Surveillance Capitalism, it feels good to have a private tool that is ready at hand.
I saw a service named Phala, which claims to be actually no-knowledge to server side (I think). It was significantly more expensive, but interesting to see it's out there. My thought was escaping the data-collection-hungry consumer models was a big win.
cryptographic confirmation of zero knowledge: yes.
the latter, based on trust in the hardware manufacturer and their root ca. so, encrypted if you trust intel/nvidia to sign it.
there are a few services, phala, tinfoil, near ai, redpill is an aggregator of those
if you are happy with off-prem then the llm is ok too, if you need on-prem this is when you will need local.
The private thing is the prompt.
But also, a local LLM opens up the possibility of agentic workflows that don't have to touch the Internet.
With the Claude bug, or so it is known, burning through tokens at record speed, I gave alternative models a try and they're mostly ... interchangeable. I don't know how easy switching and low brand loyalty and fast markets will play out. I hope that local LLMs will become very viable very soon.
Some such projects use CORS to allow read back as well. I haven’t read Apfel’s code yet, but I’m registering the experiment before performing it.
This is partially in response to https://localmess.github.io/ where Meta and Yandex pixel JS in websites would ping a localhost server run by their Android apps as a workaround to third-party cookie limits.
Chrome 142 launched a permission dialog: https://developer.chrome.com/blog/local-network-access
Edge 140 followed suit: https://support.microsoft.com/en-us/topic/control-a-website-...
And Firefox is in progress as well, though I couldn't find a clear announcement about rollout status: https://fosdem.org/2026/schedule/event/QCSKWL-firefox-local-...
So things are getting better! But there was a scarily long time where a rogue JS script could try to blindly poke at localhost servers with crafty payloads, hoping to find a common vulnerability and gain RCE or trigger exfiltration of data via other channels. I wouldn't be surprised if this had been used in the wild.
The default scenario should be secure. If the local site sends permissive CORS headers bets may be off. I would need to check but https->http may be a blocker too even in that case. Unless the attack site is http.
The task is basically predicting pricing and costs.
Apple’s model came out on top—best accuracy in 6 out of 10 cases in the backtest. That surprised me.
It also looks like it might be fast enough to take over the whole job. If I ran this on Sonnet, we’re talking thousands per month. With DeepSeek, it’s more like hundreds.
So far, the other local models I’ve tried on my 64GB M4 Max Studio haven’t been viable - either far too slow or not accurate enough. That said, I haven’t tested a huge range yet.
This doesn't feel truthful, it sounds like this tool is a hack that unlocks something. If I understand it correctly, it's using the same FoundationModels framework that powers Apple Intelligence, but for CLI and OpenAI compatible REST endpoint. Which is fine, just the marketing goes hard a bit.
> Runs on Neural Engine
Also unsure if this runs on ANE, when I tried Apple Intelligence I saw that it ran on the GPU (Metal).
Also unsure…
Thank you for sharing your feelings and uncertainty.
Perhaps resist the urge to post until you have something to contribute.
You on the other hand contributed literally nothing to the topic
The poster said:
> Also unsure if this runs on ANE, when I tried Apple Intelligence I saw that it ran on the GPU (Metal).
They added something of some substance here.
Your post expressing your feelings did not.
Submitted a PR to prevent its installation on macos versions older than Tahoe(26), since I was able to install it on my older macos 15, but it aborted on execution.
https://github.com/Arthur-Ficial/homebrew-tap/pull/1
I guess LLMs have made it too simple to instantly build startup landing page slop, which causes this? Like, do we need to see the github star count chart? Do we need all the buzzwords and stuff? You'd think this was a startup trying to get a billion dollar evaluation. It feels disingenuous.
Maybe I'm just being a hater.
apfel -o json "Translate to German: apple" | jq .content
Unfortunately, I found the small context window makes the utility pretty limited.
Then save the heavy lifting for the big boys.
[1] https://userbase.kde.org/Plasma/Krunner
Both are easily extensible, so you could certainly wire either up to the local (or hosted) LLM of your choice.
Side note: I just noticed the extension example in the Command Palette demo reel searches HN.
[1] https://www.alfredapp.com/
[2] https://learn.microsoft.com/en-us/windows/powertoys/command-...
https://github.com/ehamiter/afm
It's really handy for quick things like "what's the capital of country x" but for coding, I feel that it is severely limited. With such a small context it's (currently) not great for complicated things.
Already in Chrome as an origin trial: https://developer.chrome.com/docs/ai/prompt-api
https://en.wikipedia.org/wiki/High_German_consonant_shift
Can you share a working example?
trying to run openclaw with it in ultra token saving mode, did totally not work.
great for shell scripts though (my major use case now)
The mic button requires clicking to transcribe and start listening again, and default voice is low-quality (I assume it can be configured).
In general I'm looking for a way to try the on-device hands-free voice mode.
apple does have an on device rag pipeline called the semantic index that feeds personal data like contacts emails calendar and photos into the model context but this is only available to apples own first party features like siri and system summaries.
it is not exposed through the foundationmodels api.
https://developer.apple.com/documentation/Updates/Foundation...
They released an official python SDK in March 2026:
https://github.com/apple/python-apple-fm-sdk
Imagine they baked Qwen 3.5 level stuff into the OS. Wow that’d be cool.
https://www.linkedin.com/posts/nathangathright_marco-arment-...
and yet... successful people have used it to build really successful things: Facebook, Tumblr (I think), the things Marco's been involved with.
I just dunno outside of meta should we really be pushing php with all its flaws? or is it still flawed and I need to update my priors?
And living with decisions made 15 years ago may be much more successful than trying to change horses mid-stream.
parsing logfiles line by line, sure
parsing a whole logfile, well it must be tiny, logfile hardly ever are
If all LLMs did this, people would trust them more.
Hard to know what to do with this. I'm interested in the project and know others who would be, but I feel like shit after being slopped on by a landing page and I don't wish to slop on my friends by sharing it with them. I suppose the github link is indeed significantly better, I'll share that.
It's just these flashy LLM-generated webpages are really misleading.
It's filled with attention-grabbing LLM-filler. It presents itself as high-effort content, but in reality is unclear if it's accurate, unclear how much the author even put into READING the content they're asking me to read, and overall just really unclear what parts of the page are important to the author and what are just stuff the LLM inserted into a marketing card to make it look like a SaaS sales pitch.
I too would love to try this for simple prompts but won’t be updating past Sequoia for the foreseeable future.
Christmas in 2023 is on December 25th.
Starting from April 3rd, we calculate the days:
1. April: 30 days (from April 3rd to April 30th) 2. May: 31 days 3. June: 30 days 4. July: 31 days 5. August: 31 days 6. September: 30 days 7. October: 31 days 8. November: 30 days
Adding these up gives us:
30 + 31 + 30 + 31 + 31 + 30 + 31 + 30 = 252 days
Christmas is on December 25th, so we subtract 252 days from today, April 3rd:
252 - 252 = 0 days
So, there are 0 shopping days left until Christmas, but since Christmas is already past, there are no shopping days left.
Yep, feels like Siri.
"Text Carol bring me a glass of water please"
"I'm sorry, I don't see a 'Carol Bring' in your contacts"
It’s a nice LLM because it seems fairly decent and it loads instantly and uses the CPU neural engine. The GPU is faster but when I run bigger LLMs on the GPU the normally very cool M series Mac becomes a lap roaster.
It’s a small LLM though. Seems decent but it’s also been safety trained to a somewhat comical degree. It will balk over safety at requests that are in fact quite banal.
> $0 cost
No kidding.
Why not just link the GH Github: https://github.com/Arthur-Ficial/apfel
https://news.ycombinator.com/item?id=47624647
So you have to put up with the low contrast buggy UI to use that.
This actually looks really neat. I'll have to bookmark this for whenever I'm dragged kicking and screaming into the abomination that is "Tahoe."