Vitabile

AI Research Engineer @tether

[QVAC @qvac]

Small model. Massive logic. QVAC MedPsy-4B is here.🧠
As our benchmarks show, we are outperforming 27B models while running locally on-device. This is sovereign, private medical intelligence on YOUR hardware.
Superior methodology reverses the parameter gap.

Learn more: https://t.co/heVJq8WaJk

[QVAC @qvac]

Intelligence should not be a service you rent; it is a foundational element you possess.
At Tether, we see AI as a new element of the periodic table - a raw material that can be embedded into the very fabric of the universe.

Today, the QVAC SDK is officially live - the atomic unit for the next era of compute. From your smartphone today to the edge of the galaxy tomorrow, we are building the decentralized mind that doesn't require an uplink to function.

Infinite Stable Intelligence:
- Local-First: Runs privately on any device without permission or central servers.
- Single API: A complete SDK for Vision, RAG, P2P networking, and LLM fine-tuning.
- Unstoppable: No central point of failure if the internet breaks, your world keeps thinking.
- Decentralized: Evolve through Peer-to-Peer Swarms of Infinite Intelligence.

The era of Stable Intelligence has begun.
Start building the future at https://t.co/gsvI6w9NER.

[Paolo Ardoino 🤖 @paoloardoino]

The world is approaching a moment where billions of humans share the planet with billions of autonomous machines and trillions of AI agents.

The current model, routing every decision through a centralized server, won’t scale to meet that reality.
The laws of physics alone make centralized AI a dead end: speed-of-light latency, single points of failure, and concentration of control are features of a system designed for a smaller world.

QVAC is built for the world that’s coming.
QVAC is the fundamental building block in the era of Stable Intelligence.

[Paolo Ardoino 🤖 @paoloardoino]

Tether AI breakthrough

Tether AI team just released new version of QVAC Fabric to include the World’s First Cross-Platform BitNet LoRA Framework to Enable Billion-Parameter AI Training and Inference on Consumer GPUs and Smartphones.

Background
Microsoft's BitNet uses one bit architecture to dramatically compress models.
Traditional LLMs operate on full-precision computation, where weights are stored as complex, high-resolution numbers. The innovation of BitNet is that it shrinks these weights into a tiny ternary range of only -1, 0, and 1. significantly reducing memory usage and computation.
LoRA, is a parameter-efficient fine-tuning technique that reduces the number of trainable parameters by up to ninety-nine percent.
Together they slash memory and compute requirements. Yet BitNet has mostly been limited to CPU or CUDA NVIDIA backends, and lacked the support of LoRA fine-tuning.

Enters QVAC Fabric: the unlock
Today, with QVAC Fabric LLM, is the first time BitNet LoRA fine-tuning and inference work cross-platform across GPU vendors and operating systems using Vulkan and Metal backends.
That means support for AMD, Intel, Apple Metal and also Mobile GPUs.
And for the first time ever, BitNet inference runs efficiently on smartphones using mobile GPUs.
On flagship devices, GPU inference is 2 to 11 times faster than CPU while using up to 90% less memory than the full precision models.

The biggest unlock: QVAC Fabric LLM support for BitNet LoRA fine-tuning on heterogeneous GPUs. Our team was able to demonstrate this by fine tuning models up to 3.8 billion parameters on all flagships phones such as Pixel 9, S25 and iPhone 16 and up to 13 billion parameter models on the iPhone 16.

Github repositories:
https://t.co/UxvXHYpRiy : general QVAC Fabric codebase
https://t.co/dFlbXK1kuQ : specific QVAC Fabric's BitNet knowledge base, architecture docs and pre-built binaries

What does it mean?
What used to require dedicated GPUs now runs on consumer hardware.

This breakthrough is the first real-world signal of a local private AI that can truly serve the people.
And this is just the beginning.
In the next months and years Tether will relentlessly continue to invest significant amounts of resources and capital to continue to research and develop open-source intelligence that can scale and evolve on local devices, providing maximum utility and privacy to its users.

The era of Stable Intelligence has just begun.
Free as in freedom.

[Tether @tether]

Tether’s QVAC Launches World’s First Cross-Platform BitNet LoRA Framework to Enable Billion-Parameter AI Training and Inference on Consumer GPUs and Smartphones
Learn more: https://t.co/8ygOFzhfjn

[Tether @tether]

Tether EVO Scores Top 5 In Global AI Benchmark for Brain-to-Text AI Challenge
Learn more: https://t.co/sVruUaAzvc

[Tether @tether]

⛏️ Bitcoin Mining is complex.
️⚡ Mining OS by Tether (MOS) makes it simple.

Introducing MOS — the open-source operating system for real mining infrastructure.

Modular. Scalable. Built for energy + hardware + data.

Explore the Documentation: https://t.co/FZF93sTwkn
Join our Discord and ask questions https://t.co/sHeF6qly6l

[Tether @tether]

🚨 At @PlanBElSalvador? Come visit the Tether booth 🇸🇻

Discover our latest projects:
⚙️ QVAC – Local AI
🔌 MOS – MiningOS
🔐 WDK – Wallet Dev Kit
🧱 Hadron – Asset Tokenization
…and more.

Ask questions, connect with our team, and see what’s next!

[QVAC @qvac]

Introducing QVAC Health, the all-in-one wellness platform that aggregates your health data from various sources in one, encrypted, offline-capable environment. Say goodbye to fragmented data and hello to a unified, AI-powered wellness timeline!

QVAC - Your Device, Your AI

https://t.co/qcwATHQpig

[QVAC @qvac]

Introducing QVAC Fabric LLM: The framework that brings full AI inference and fine-tuning to your hardware.

Execute and Fine-tune modern models like LLama3 and Gemma 3 on your laptop, your consumer GPU, and even your smartphone.

No cloud. No compromise. You control your data.

QVAC Fabric LLM is open source. It’s decentralized, hyper-scalable, antifragile, user-controlled AI.

QVAC, your device, your AI

Learn more: https://t.co/O0K5FT3b4J

[Paolo Ardoino 🤖 @paoloardoino]

Intelligence won't be centralized or closed. Mark my words.

[QVAC @qvac]

🚨QVAC Workbench is now live on iOS and Android!

Run powerful AI models locally on your phone — no cloud, no compromise.
Private & Peer-to-peer.

Try it now on iOS 👉 https://t.co/O4NYvPvoZ5

Try it now on Android 👉 https://t.co/FbkP9hD8GD

[Paolo Ardoino 🤖 @paoloardoino]

Tether's AI first launch.
Local on-device AI is evolving.

- QVAC Workbench, mobile/desktop app for using and experimenting many AI models locally on device with 100% privacy
- QVAC Genesis I, largest synthetic pre-training datasets for Large Language Models (LLMs) to date.

🤖🤖

[QVAC @qvac]

What if anyone could train world-class AI—without big tech, without billions?
Introducing QVAC Genesis I:
The largest and highest-quality multi-domain educational synthetic dataset for LLM pre-training.
41B tokens. Clean. Structured. Built for reasoning, not scraping.
Open data for open intelligence.
We’re unstoppable together.
Learn more: https://t.co/a1lekWE3Cw

[Tether @tether]

Tether Releases QVAC Genesis I, World’s Largest Synthetic Data Set to Train STEM-Focused AI Models, Alongside QVAC Workbench, a Comprehensive Local AI App
Read more: https://t.co/KVDap1l9GQ

[Paolo Ardoino 🤖 @paoloardoino]

Please meet Subash, the Head of Tech @tether
( @pingsns his twitter profile )

In this video Subash talks about QVAC, Tether's Local AI Platform, using the Holepunch stack as runtime and peer-to-peer layer ( https://t.co/hoYR7Tdjmo )

Enjoy 🤖

https://t.co/Jw2o2upr4B

[BitPolito @bitpolito]

Finalmente #Bitcoin verrà insegnato nei licei!
30 ore di lezione, sia teoriche che pratiche, tenute dai nostri ragazzi e da speaker di livello internazionale.
Grazie agli sponsor: @conio @bitbox e Politecnico di Torino.
Un esercito di #bitcoiner è agli albori, stay tuned!
#BGen