Hacker Newsnew | past | comments | ask | show | jobs | submit | terhechte's commentslogin

Is there a way to run these Omni models on a Macbook quantized via GGUF or MLX? I know I can run it in LMStudio or Llama.cpp but they don't have streaming microphone support or streaming webcam support.

Qwen usually provides example code in Python that requires Cuda and a non-quantized model. I wonder if there is by now a good open source project to support this use case?


You can probably follow the vLLM instructions for omni here, then use the included voice demo html to interface with it:

https://github.com/QwenLM/Qwen3-Omni#vllm-usage

https://github.com/QwenLM/Qwen3-Omni?tab=readme-ov-file#laun...



Whisper and Qwen Omni models have completely different architectures as far as I know

I wish they had a working ARM port

CachyOS would require Arch Linux to implement the support first. Progress is slow but steady:

- https://lists.archlinux.org/archives/list/arch-dev-public@li...

- https://rfc.archlinux.page/0032-arch-linux-ports/


Adding onto this, progress is moving faster thanks to Valve contributing to efforts such as buildbtw for arch.

Not out of the goodness of valve's heart either, they want it for arm based steamOS devices like the frame. A win win for many though.


Tired: x86_64 Wired: arm64

I'm curious, what hardware would you run it on?

I oftentimes run Linux Desktop fullscreen in a VM on macOS. macOS acts like a hardware abstraction layer in that case. Depending on the task and the tools, I sometimes prefer this option (I do like the macOS UI though (except for the current version), I just like to use the right tool for the job)

M2 Ultra Mac Pro with 192GB RAM?

Fully agree to this. LM Studio is much nicer to use and with MLX faster on Apple Silicon


Weird, I didn't get that question. It asked for full disk access so it could import my Safari settings, but that was optional.


Hey Marcin :) Really dig this. A much friendlier alternative to Swift development than having to use the monstrosity that is Xcode. Especially for people that want to get something done quickly. The Linux support is also really cool. The Xcode-alternatives market is really starved, so I'm very happy this exists. It's possible to configure VSCode to support Swift, but that's a lot of configuration and messing around.

When Vim bindings? ;)


it works really great with https://kindavim.app/ which adds vim everywhere. problem solved.


I also stumbled upon https://github.com/FelixKratz/SketchyVim but haven't used it yet, though I am using JankyBorders


Thanks for sharing! Not sure why I never looked for something like this as I’ve tried to inject vim everywhere I can.


Is there anything like this for Linux? Or at least for individual UI systems (GTK etc.)?


> but that's a lot of configuration and messing around.

Maybe I’m missing something but the last time I did this I clicked “install” on the official Swift VSCode extension and that was it. Not a lot of messing around needed, for me at least!


You needed to own a "QuickTime Pro" license in order to enable these features. I used to do all my simple video editing with it until they shelved it.


You're thinking of QuickTime 7, that can be optionally installed (as a separate app) even on macOS 10.14 Mojave! But the website is referring to versions of QuickTime X. QuickTime 10.2, which was included with Mountain Lion, was the last to support third-party components. (If you've ever used "Perian", that's what I'm referring to.)


I can see the labels when I hover with the pointer


I tried it some weeks ago, but I went back to the CLI. Honestly, I've been a GUI app for most of my life, preferring proper GUI tools to Terminal tools, including running the GUI versions of VIM and Emacs (during my brief emacs stint). However, over the past 2 weeks I've slowly transitioned to a full cli development setup with wezterm, neovim, lazygit, fzf, fish & Claude Code. I enjoy working like this so much.


> Honestly, I've been a GUI app for most of my life

Don't worry, someday you'll grow wiser and maybe you'll spend some time living as a CLI executable.


I've by now come to the belief that there's someone high ranking in Apple Org responsible for iPad who deeply despises developers. Every action done over the past years has made development on the iPad worse, not better. Such as spending extra legal energy to make sure the recently-introduced emulator support on iOS does not cover running any kind of computer VM that could allow software development. At the same time, Android ships an official terminal that can run a Debian VM and X11 apps.


Apple is a consumer company. They're all about catering to the consumer class, and growing that class at any price.

Developers are necessary, and their needs has to be tolerated, but only as long as they are successfully kept distinct from consumers.


It's one thing to not have your needs directly catered to and delivered on a silver platter.

It's another to have the company go far out of their way to they don't even leave the field open for someone to cater to your needs.


I don't think that's true at all. Apple has always marketed itself as a brand for creatives. Image/video editing and 3D modeling software demands a lot from its hardware, just like developer tools do. But removing restrictions on developer tools is inherently a security risk, and Apple seems very willing to ship less capable devices if they're also less vulnerable.


Android is no panacea either. There are no Android tablets that are anywhere close to achieving parity with the iPad.

I used a Samsung Galaxy Tab S8+ with the Book Cover (the one with the track pad) and the Smart Folio (the one without a track pad).

The track pad was horrible. HORRIBLE. Ghost taps, misfired scrolls, and cheap feeling clicks. The track pad on the Magic Keyboard is as good as the standalone Magic Trackpad; this didn't even come close in quality.

The keyboard was fine, but keyboard shortcuts are implemented on a per app basis. This is fine until you want to use CTRL+L in Firefox to navigate to some URL only to discover that Firefox simply doesn't support keyboard shortcuts! Someone opened an issue for this two years ago too because, insanely enough, FF used to support them but simply dropped them because "reasons."

Then there was the cover. The Book Cover provides a Surface like kickstand that's adjustable. Great on a table; unusable on your legs. The Folio solves this by using a tented support, but this forces the tablet into a 25-ish degree tilt that I didn't find comfortable. There wasn't anything like the Magic Keyboard's excellent magic hinge (though maybe later model Galaxy Tabs have an equivalent).

All that said, Termux worked GREAT, and I think I would've gotten mileage out of using an external screen with DeX though I've heard it's lacking in that department. I badly wanted this setup to work, but there were too many quirks.

Also, battery life sucked.


They despise users becoming developers. Apple's entire model depends on these being separate groups of people (as opposed to GNU/Linux OSes where they're assumed to be exactly the same.)

Keeping development tools away from users gives Apple a substantial amount of power over them that they can rent out to approved software development organizations.


That is Microsoft. Apple for small developers just paid $100 per year got you there. And tbh the terminal and underlying unix shell is real.


Ironically it's easier to run a compiler and do whatever you like on Microsoft's OSes these days.


the _6!_


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: