Paolo Ardoino 🤖
@paoloardoino • 348,793 subscribers
CEO @tether 🖇️ + CTO @bitfinex 🍀 | @keet_io 🍐 + https://t.co/arlfWS9TE7 @QVAC 🤖 + 🦓 (Views are my own)
Shorts
Videos
QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.
Paolo Ardoino 🤖41,845 views • 1 month ago
QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.
Paolo Ardoino 🤖142,533 views • 6 months ago
The cloud has failed us. Again. 16 billion passwords just leaked. It’s time to ditch the cloud. That’s why we’ve been building PearPass — coming soon. A fully local, open-source password manager. No cloud. No servers. No leaks. Ever. Just you — and your keys, stored securely on your devices.
Paolo Ardoino 🤖164,905 views • 11 months ago
🇮🇹🇮🇹🇮🇹 Tether invests in Generative Bionics, spinoff of IIT (the Italian Institute of Technology), to support the development of a new generation of intelligent humanoid robots. The future of robotics is local on-device AI ( ), programmable money (Bitcoin, USDT, USAT, XAUT) and self-custodial wallets (WDK, Wallet Development Kit).
Paolo Ardoino 🤖85,033 views • 5 months ago
Yesterday at Lugano Plan ₿ I presented a preview of Tether's Local AI development kit, privacy focused, powered by peer-to-peer technology 🍐🍐 Write the code once, and run everywhere, from a 40$ phone, to a flagship smartphone, from a laptop to a mainframe with many H100, from a smart fridge to a car entertainment system. Based on 🐻 Terher's AI SDK is extremely modular, it uses supports any model (Marian, Llama, ...) and loads/stores weights and fine-tuning data in P2P data structures. Open source once battle tested. Demo of a sample local and 100% private translation app working on any device 👇
Paolo Ardoino 🤖127,841 views • 1 year ago
Here is a demo of the (Wallet Development Kit) WDK Template Wallet. - build 100% on WDK by Tether - well encapsulated reusable UI components - soon opensource - fully non-custodial (supports different seed backup strategies to enable super simple user-experience) - available for any platform/os both mobile and desktop - implements USDT, USDT0, an extremely comprehensive set of DeFi primitives (lending, swapping, ...) - security audited - clone, add your customizations, build and release to your community - team is doing an incredible job, very proud WDK by Tether will be the building block for billions of wallets.
Paolo Ardoino 🤖55,060 views • 8 months ago
#lugano #planb and #bitcoin at Bellinzona Carnival fest 🇨🇭🍫🐮
Paolo Ardoino 🤖134,700 views • 3 years ago
iOS support for Tether's upcoming AI runtime works well now. Translations are fully local, fully private. Model's weights are downloaded from P2P network (Holepunch) the first time you use the app. Unstoppable, resilient. Write code once in JavaScript ( ) and run it everywhere, on any device. Marian, Llama and Whisper fully supported. Can't wait to open source it.
Paolo Ardoino 🤖74,039 views • 1 year ago
Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon
Paolo Ardoino 🤖42,015 views • 10 months ago
QVAC Translate is becoming amazing. 100% local on device, 100% private. Supports already tens of languages. Audio and video translation. Working now on: - translation of any document in any format to any format - real-time conversation translation Team is impressive. In private beta now. Powered by QVAC SDK. Soon at
Paolo Ardoino 🤖34,169 views • 9 months ago
