Rich Dunbar

Nexus Adapter Studio is an experimental browser-based WebGPU application for training LoRA adapters on supported GGUF models. Bring your own model and JSONL corpus, evaluate learning, and export resumable Nexus adapter checkpoints. Runs locally without a Python or PyTorch backend.

Nexus AI Studio is an experimental browser-based AI workspace with local WebGPU inference, supported GGUF model loading, voice interaction, optional facial-expression cues, retrieval-based memory and adapter learning. Built for customizable, privacy-conscious local AI.

NEXUS Imaging Studio is a Windows-based USB imaging and recovery platform featuring bootable ISO flashing, disk management, forensic file recovery, verified data erasure, and AEGIS adaptive recovery with advanced safety controls.

NEXUS LittleBit Compression & Recovery is an experimental AI platform supporting ultra-low-bit LLM quantization (8 to 0.1 BPW), custom AMD/WebGPU-accelerated inference, and five-stage recovery using up to 10 million training tokens. Designed to advance efficient, sovereign, offline AI on consumer hardware.

Nexus ZLC is an experimental offline toolkit for lossless GGUF compression and compressed-weight inference. It preserves original model data, supports compatible models through a custom WebGPU engine, and includes restoration and before-and-after perplexity tests.

NEXUS Web LLM is a browser-based local inference app for compatible GGUF and LittleBit models, featuring custom WebGPU acceleration, metadata-driven configuration, 100 model profiles, automatic memory planning, speed tuning, and runtime diagnostics.