Blog

Articles, guides and deep dives from the QVAC team.

Announcements Models Research SDKJuly 16, 2026

Nothing is more private than a thought: how QVAC runs a brain-to-text model fully on-device

For people who have lost their voice to ALS, the words are still there. The connection to the world is what breaks, not the mind. BrainWhisperer, from Tether Evo, decodes attempted speech from the brain into text, and QVAC runs it fully on-device: more than 90% of words correct on real recordings, in under 2 GB, nothing leaving the machine. An early proof of concept, not a product.

Fabric ResearchMarch 17, 2026

LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric

The world’s first framework to enable BitNet fine-tuning with LoRA on GPUs enabling fine-tuning on edge devices substantial performance improvements

Genesis ResearchDecember 19, 2025

QVAC Genesis II: Expanding the Largest and Highest-Quality Multi-domain Educational Synthetic Dataset for LLM Pre-training

Building upon the success of Genesis I, we introduce QVAC Genesis II, a major expansion that adds new domains and a total of 148 billion tokens.

Fabric ResearchDecember 1, 2025

An Edge-First Generalized LLM LoRA Fine-Tuning Framework for Heterogeneous GPUs

We present a unified, cross-platform framework that successfully enables parameter-efficient training of modern LLMs with LoRA on consumer hardware such as mobile SoCs and desktop GPUs, without relying on a CUDA-only ecosystem.