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 2 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.
hombre_fatal 28 minutes 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.
ge96 2 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 2 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
lukewarm707 3 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 2 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 2 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.
djl0 1 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.
mark_l_watson 2 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.
aswanson 3 hours ago [-]
That's the way things have to go. Business risk is too high having everything ran over exposed networks.
lukewarm707 3 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 2 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 3 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 3 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 5 minutes 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 4 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 4 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 3 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 4 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 4 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 3 hours ago [-]
Keep seeing similar mistakes with vibe coded AI & MCP projects. Even experienced engineers seem oblivious to this attack vector
snarkyturtle 3 hours ago [-]
Noting that there's an option to require a Bearer token to the API
Multiplayer 2 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.
lewisjoe 43 minutes 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!
gurjeet 20 minutes 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.
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.
Unfortunately, I found the small context window makes the utility pretty limited.
troyvit 2 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.
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 55 minutes 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.
khalic 5 hours ago [-]
AFM models are very impressive, but they’re not made for conversation, so keep your expectations down in chat mode.
VanTodi 3 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.
mattkevan 3 hours ago [-]
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.
Phemist 2 hours ago [-]
Nice! The example should imo say
apfel -o json "Translate to German: apple" | jq .content
EddieLomax 2 hours ago [-]
This is similar to something I was playing around with last month-- basically just a CLI for accessing the foundational models.
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.
divan 1 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.
Barbing 3 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)
arendtio 3 hours ago [-]
For those who don't know, 'Apfel' is the German word for Apple.
gherkinnn 3 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.
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.
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?
nose-wuzzy-pad 3 hours ago [-]
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 3 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.
3 hours ago [-]
mark_l_watson 2 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.
swiftcoder 5 hours ago [-]
Anyone tried using this as a sub-agent for a more capable model like Claude/Codex?
LatencyKills 5 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.
khalic 4 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 3 hours ago [-]
> [Qwen coder 0,5B] can output decent functions given the right context instructions
Can you share a working example?
khalic 3 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
franze 5 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)
satvikpendem 1 hours ago [-]
How does this model compare against other local models like Qwen run through LMStudio?
furyofantares 1 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.
als0 3 hours ago [-]
Is this for Tahoe only? I’m still clutching onto Sequoia
anentropic 2 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 2 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 55 minutes 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.
elcritch 5 hours ago [-]
Any know if these only installed on Tahoe? I'm running Sequoia still and get an error about model not found.
HelloUsername 5 hours ago [-]
> Apple Silicon Mac, macOS 26 Tahoe or newer, Apple Intelligence enabled
jonpurdy 3 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 1 hours ago [-]
Same. What a disaster Tahoe is.
gigatexal 5 hours ago [-]
It’s a very small model but I’ve been playing with it for some time now I’m impressed. Have we been sleeping on Apple’s models?
Imagine they baked Qwen 3.5 level stuff into the OS. Wow that’d be cool.
bombcar 4 hours ago [-]
Apparently the Overcast guy build a beowulf cluster of Mac minis to use the Apple transcription service.
For small tasks this seems perfect. However it being limited to English from what I can tell is quite a downsite for me.
thenthenthen 5 hours ago [-]
The vision models and OCR are SUPER
Oras 4 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 4 hours ago [-]
Making a sentence out of a json
p1anecrazy 5 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 5 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 30 minutes ago [-]
the model prefers to tell you nothing before it tells you something wrong
If all LLMs did this, people would trust them more.
joriskok1 3 hours ago [-]
How much storage does it take up?
franze 2 hours ago [-]
4mb download, after install about 15mb, model is already on your mac with mac os x tahoe
pbronez 3 hours ago [-]
Digging into this, found Apple’s release notes for the Foundation Model Service
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.
api 3 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.
phplovesong 3 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).
adettya009 39 seconds ago [-]
[dead]
aiiaro 1 hours ago [-]
[dead]
brtkwr 3 hours ago [-]
[dead]
7 hours ago [-]
volume_tech 3 hours ago [-]
[dead]
devcraft_ai 59 minutes ago [-]
[dead]
5 hours ago [-]
Remi_Etien 6 hours ago [-]
[dead]
3yr-i-frew-up 3 hours ago [-]
[dead]
reaperducer 1 hours ago [-]
[dead]
animanoir 2 hours ago [-]
[dead]
hackerman70000 3 hours ago [-]
[flagged]
skrun_dev 7 hours ago [-]
Notes.app handles big notebooks without choking on storage?
ramon156 4 hours ago [-]
Cool tool but I don't get why these websites make idiotic claims
So the full solution would be models trained in an open verifiable way and running locally.
You can trigger the the service's ToS violation or worse, get tipped off to law enforcement for something you didn't even write.
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
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.
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.
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.
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.
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
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
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.
apfel -o json "Translate to German: apple" | jq .content
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.
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.
https://en.wikipedia.org/wiki/High_German_consonant_shift
Already in Chrome as an origin trial: https://developer.chrome.com/docs/ai/prompt-api
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.
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)
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.
I too would love to try this for simple prompts but won’t be updating past Sequoia for the foreseeable future.
Imagine they baked Qwen 3.5 level stuff into the OS. Wow that’d be cool.
https://www.linkedin.com/posts/nathangathright_marco-arment-...
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.
https://developer.apple.com/documentation/Updates/Foundation...
They released an official python SDK in March 2026:
https://github.com/apple/python-apple-fm-sdk
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.