Nexural vs Gadeon

Nexural is a privacy-first AI assistant that runs directly on your iPhone. Ask questions, write, summarize, brainstorm, and plan — without sending your prompts to a server for processing. WHY NexurAl • On-device inference: your prompts are processed locally during normal use • Works offline (after setup) • No accounts required • No training on your chats • Share only when you choose HOW IT WORKS Language models are the “brain” behind an AI assistant. NexurAl runs a model on your device (bundled with the app or downloaded in the app). Your text stays on your iPhone, and responses are generated locally. NEXURAL PRO (Subscription Required): Upgrade to unlock the full power of local on-device AI: - Premium Model Catalog: Access our full library of advanced, high-parameter models. - Pro Optimizations: Experience peak performance and security with Metal Acceleration, Speculative Decoding, Context Compression, Thermal Guard, Streaming Tokens, and the Encrypted Vault. PRIVACY IS THE FEATURE Many AI tools rely on the cloud. That can mean your private text is transmitted to servers and may be stored or used to improve models (depending on the provider). Nexural avoids that tradeoff by keeping AI processing on your device. IMPORTANT NOTE AI outputs can be inaccurate. Don’t rely on NexurAl for medical, legal, financial, or emergency decisions. Support: support@nexural.net Privacy policy: https://nexural.net/privacy.html

Gadeon runs Qwen3.5 and QwenPaw hybrid language models entirely on your device's Apple Neural Engine, using Core ML as its only framework dependency. There's no C, no Python, and no cloud calls: every token is generated locally, keeping your conversations private. Under the hood, these models mix Gated DeltaNet recurrent layers with a smaller number of attention layers. Gadeon compiles that hybrid architecture directly onto the Neural Engine's dataflow accelerator, so both prompt processing (prefill) and token generation (decode) run on-chip instead of falling back to the CPU or GPU. On an Apple Silicon Mac, prefill measures roughly 2 to 2.4 times faster and about 4.4 times more energy-efficient per token than a Metal GPU baseline, while leaving the GPU free for other work. Conversations in Gadeon are append-only: each turn extends the model's fixed-size recurrent state instead of re-processing the entire chat history, so response latency doesn't grow as a conversation gets longer. The app can also roll back to an earlier point in a conversation, dropping reasoning traces or replaying tool calls in a clean form without reprocessing everything from scratch. For ternary-quantized models, Gadeon switches to a pure-Swift Metal GPU backend behind the same session and tokenizer interface, so both compute paths feel identical from the chat UI. Gadeon is a proof of concept for bringing Gated DeltaNet hybrid models to the Neural Engine through Core ML - built to explore what's possible on Apple's own silicon.