Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines.
Joined April 2025
- Tweets579
- Following2
- Followers12.7K
- Likes33
Reminder: the QVAC SDK runs more than 20 generation models locally, including image, video, music, voice and sound effects.
Why not just run everything in the cloud?
"What if the connection drops and the robot cannot connect anymore to the data center? Will the robot stop?"
@paoloardoino, CEO of Tether
Agent Emergence put QVAC inside an actual 2 GB camera, with detection on its NPU, VisionPsy-Nano describing the scene, and not a single frame leaving the device.
They started from our open-source smart camera example and built on it to create this awesome real-life demo. Not only did they connect it to a real camera, they also optimised it by running detection on the neural processor and the analysis on the CPU.
Brilliant.
1/9 @qvac built a smart camera that never uploads your footage, running on a laptop.
We put the same idea inside an actual camera: QVAC on a 2 GB device, detecting on its NPU, describing with VisionPsy-Nano, and proving that no frame ever left. 🧵
We love to see more builders building with QVAC.
Here, Fabiana built a demo for a medical scribe that drafts the patient note on the phone, fully offline.
A doctor wants to see the patient, not the keyboard. AI scribes help, but most send sensitive visit data to the cloud.
So I built a @qvac prototype: record the visit, get a draft SOAP note, all on the device and offline.
Waiting for TranscribePsy on the SDK.
The AI Yako hackathon kicks off this Saturday, 24 October, at Node NBO in Nairobi, and demo day is 31 October.
Teams build AI that runs on their own device with QVAC, on three tracks: offline AI apps, moving a cloud product onto the device, and on-device agentic finance with WDK. Projects are judged with the internet switched off.
Register here: luma.com/tv34ngtp
ALT AI Yako, Own Your AI hackathon flyer by QVAC and Node NBO, 24 to 31 October 2026, Node NBO campus, Nairobi
Should a few companies own all of AI?
"Imagine how crazy it would be that two, three, four companies are going to handle all the intelligence for the entire humanity for the rest of the future."
@paoloardoino, CEO of Tether
Why should AI be local first?
"Humanity should invest in AI that is local first, that is owned by the people, that is available and inclusive to everyone."
@paoloardoino, CEO of Tether
Half of Europe couldn't reach their bank app yesterday because one data center in London lost power.
Now imagine the same outage taking down the AI your business depends on.
Wild idea, but what if access to intelligence didn't need a data center?
Our PM can’t even take a flight without coming back with a QVAC prototype. This one turns any exam curriculum into practice tests, and it works without internet.
Want to give it a try or build on it?
It's accessible here: github.com/tetherto/qvac-exa…
It's fascinating how many real life use cases there are where local AI is so handy.
I was on a plane with my girlfriend and she was learning for a certification, while randomly complained that she couldn't practice on real tests (low cost life, no internet 😆)
Of course a @qvac prototype popped into my head -> you feed in some exam curriculum and you get tests based on it, works offline, and you can generate as many tests as you want, for free.
The power and beauty of local AI is amazing.
You can now run Laya with QVAC, an open source decision model from ConvAI Innovations.
Laya answers your questions about a piece of text.
In this first video, you can see it play a runner game: for each object coming its way, it decides whether to grab it or jump over it, based on a rule you pick, such as "This is an animal."
Laya takes three kinds of question: yes or no, one option from a list, or a place on a scale, from not urgent to blocking.
It comes in three versions: English (421M parameters), multilingual (322M), and typed decisions (421M), fine-tuned on business workflows such as invoice processing and customer service.
Load Laya with loadModel, then pass your text and questions to decide().
Docs: docs.qvac.tether.io/sdk/refe…
QVAC SDK 0.22 is out, and it adds Laya, a model that makes decisions instead of writing text.
We added:
- Laya support: answers the questions you define, each with a probability
- CUDA support: for LLM, embedding and VLA models.
- MiniMax-H3 image to video: start a clip from your own picture
- MOSS-SoundEffect v2: create sound effects on device
- Model fit checks: broader model coverage, improved estimates for model combinations, and opt-in load refusal before model loading begins
- Parallel tool calls: agents run several tools in one turn
Learn more in the thread below.
Complete release doc here: github.com/tetherto/qvac/rel…
Star ⭐️ for updates.
Other items:
- The KV cache now lives inside the addons: apps can send the whole conversation each turn, as with any OpenAI-style API, and the addon reuses the part it already processed
- MiniMax Music 3 speed improvement on an RTX 5090: up to 28% faster on CUDA and 20% faster on Vulkan (f16).
- Optimizations to Audio8, Parler and CosyVoice speech that now run faster on Apple silicon
Fabric moves to llama.cpp b11018 (@qvac/fabric 0.20.0). The shared runtime is rebased onto upstream llama.cpp b11018, and the addons built on it are re-released to match.