Gabber

Inference for real-time voice, text, and video models + orchestration to build realtime apps that can see, hear, speak, and do

[Jack @jackndwyer]

One thing we've been excited about since the beginning of Gabber is Avatars

Here we have Visemes animating the mouth on a ThreeJS rendered realtime AI powered VRM avatar

[Gabber @GabberDev]

@jackndwyer Very cool

[Jack @jackndwyer]

Can I build a realtime basketball coach that counts my shots and gives me voice feedback on my jump shot?

Using Qwen3-VL 30B and a conversational AI, I found out - build tutorial at the end

Link to try it below

[Jack @jackndwyer]

Stumbled upon this video on youtube

Word is getting out

https://t.co/obdyKmumTM

[Gabber @GabberDev]

@jackndwyer @sharifshameem @tamrrat @_tlynch @r0bwiki @jmdagdelen @anishthite @BrianBlumenfeld @landogregg @Do_owne Good ideas here, let's get to building

[Gabber @GabberDev]

@jackndwyer Fantastic

[Jack @jackndwyer]

Introducing Gabber

Realtime, multimodal AI inference + orchestration for Vision, Speech, and Language Models

Build AI that can see, hear, talk, call tools, and do anything for $1/hr

[Gabber @GabberDev]

https://t.co/gsZLPRCaaJ

[Gabber @GabberDev]

Qwen3-VL 30B + Gabber

[Jack @jackndwyer]

I built an AI personal trainer that counts reps for me

It went a little bit horribly wrong, but it mostly worked great

I'll link a blog post on exactly how I built it below

[Gabber @GabberDev]

@jackndwyer Very nice

[Brian Blumenfeld @BrianBlumenfeld]

Building real-time personal co-pilot that can see your screen and talk with you at @GabberDev.

[Gabber @GabberDev]

A real-time learning assistant that sees your screen, talks, and learns alongside you. All open-source models (Qwen3-VL, Parakeet, Orpheus) wired together

Homework, research, studying - all made easier

Watch the video to see just how well it did

[Jack @jackndwyer]

You can Video chat with Qwen3 Omni right now

We're hosting the 30B Instruct and it's fast and pretty versatile

[Jack @jackndwyer]

Want to build a simple realtime AI app in 5 min?

Here's a tutorial on how you can create a conversational AI that runs on your laptop

[Brian Blumenfeld @BrianBlumenfeld]

Turned @Alibaba_Qwen 3-Omni into a screen-aware code copilot. It watches @dwyer_neil 's screen, catches issues problems, and suggests fixes. Ran on H100 (FP8 Dynamic Quant) via @GabberDev

[Brian Blumenfeld @BrianBlumenfeld]

@GabberDev is closing in on its first 1k GitHub Stars

https://t.co/bzmdpGTZa7

[Brian Blumenfeld @BrianBlumenfeld]

New open-source multimodal models are wild. They don’t just read and write, but can see, hear, and think.

Here’s @Alibaba_Qwen Qwen3-Omni (thinking mode) running locally on an H100.

Smarter than 2.5, handles voice, tool calls, and real-time context.

@GabberDev will set these models free.

[keepingitneil @dwyer_neil]

@Franzferdinan57 @TheAhmadOsman Check us out @GabberDev we’re going to be hosting it by EOD

[Gabber @GabberDev]

@jackndwyer I agree

[Gabber @GabberDev]

RT @jackndwyer: I think it's stupid that I have to write things when AI can now see and hear

So I built an AI that:
- talks to me
- contin…