DISTRIBUTED INTELLIGENCE NETWORK

The world's GPU,
united.

The cheap, open alternative for AI: chat, image/video/audio generation, and a developer API — all served by a worldwide network of community GPUs. Pay with crypto. Earn by plugging yours in.

// Windows may warn "unknown publisher" on new apps, click Keep, then Run anyway

n1o network · live
0nodes online
0 GBGPU memory contributed
0tokens served
awaiting nodes, the network ignites when the first model's memory is gathered
01 / WHAT YOU GET

Open AI that undercuts the giants

You don't come here to pay Big Tech prices. Open models — chat, media and an API — served cheap by a community GPU network. Enough for most work, at a fraction of the cost.

AI chat & agent

Multi-model chat plus n1o Code, an agent that works in your real files. Open models, far cheaper than the closed labs.

Media generation

Image, video, audio and voice from open models — the kind that's gated or pricey elsewhere. The GPU network is built for it.

Developer API

One endpoint for open models (Llama/Qwen-class): cheap, usage-based, no lock-in. Build your app on inference you can actually afford.

Crypto-native

Wallet login, pay with crypto, no data harvesting. Community-owned — and you can earn by contributing your GPU.

02 / THE NETWORK

One model, thousands of GPUs

What BitTorrent did for files, n1o does for intelligence. Large models live in billion-dollar data centers. We split them instead: each person hosts a slice of the model on their own GPU, and answers travel across the swarm. Nobody owns it whole, everybody runs it.

step_01

Connect your GPU

One click in the desktop app. A slider sets how much memory you contribute, the rest stays yours for gaming and work.

step_02

The swarm serves real work

Every request to the community model travels through the network's GPUs. Open models, owned by everyone, owned by no one.

step_03

Earn for what you process

Proof of Inference: n1o points for every token YOUR card actually processes, not for sitting idle. A future $n1o token for redemption is being explored — it may never launch.

// experimental — points are an internal record of useful work; any future $n1o token or redemption is exploratory, not a promise, and may never happen

03 / ENTERPRISE

GPU infrastructure for AI companies

Run, test and scale open models on a planet-wide pool of consumer GPUs.

The n1o network aggregates people-powered GPU capacity into a single programmable layer. AI companies use it as complementary infrastructure, alongside their own data centers, not instead of them.

Burst inference capacityOffload open-model traffic peaks to the network and pay per completed request, no reserved instances, no idle spend.
Model testing at real-world scaleEvaluate builds and fine-tunes across thousands of heterogeneous consumer devices: real latency, real hardware, before release.
Managed open-model APILlama- and Qwen-class models served through one endpoint, with volume pricing and usage-based billing.
Edge distributionInference served from nodes geographically close to end users, reducing round-trip latency for global products.
Contact partnerships →
04 / DOWNLOAD

One app, every desktop

Native builds for the three major platforms, signed and self-updating. Install once — every new version arrives on its own.

Windows

64-bit installer (.exe) · system tray, global shortcut, GPU node
Download

macOS

Apple Silicon (.dmg), signed with an Apple Developer ID
Download
first launch: right-click → Open

Linux

AppImage, runs on any distro · GPU node included
Download
curl -L -o n1o.AppImage \ https://api.n1o.ai/releases/latest-linux chmod +x n1o.AppImage ./n1o.AppImage
// auto-update built in: when n1o improves, every install follows on its own
05 / MINING FARMS

Rigs idle since Ethereum? Put them on AI

The n1o headless node runs on any rig with a terminal: no screen, no reinstall, no new OS. Two commands and every GPU in the farm earns for the AI work it serves.

HiveOS

From Hive Shell

Your worker → Remote Access → Hive Shell. Paste the commands below and the node starts with the rig from then on (systemd).

RaveOS

From the web console

Workers → your rig → Console. Same commands — python3 is already there.

SSH

Any Linux rig

Ubuntu, Debian, whatever your farm runs. If you can SSH in, you are 30 seconds away.

curl -sL https://n1o.ai/node.sh | sh # tu GPU responde y gana puntos de trabajo (descarga el modelo la 1a vez): n1o-node --token YOUR_TOKEN --servir # que arranque solo con el rig: sudo n1o-node --servicio --servir

// disk: to just contribute VRAM the agent is under 1 MB, any disk works. To serve the model (and earn work points) the rig downloads it once: ~5 GB for an 8-GB card, ~9 GB for 12 GB, ~20 GB for 24 GB. A 32 GB system disk covers every tier up to Pro.

// YOUR_TOKEN lives in app.n1o.ai → n1o Network → "Vincular por consola" · points go to your account, one token links your whole farm

# FASE 2.1 · reparto de capas entre varias GPUs (misma cuenta) # el MISMO comando en todas tus máquinas — la red hace el resto: n1o-node --token YOUR_TOKEN --rpc

// reparto: cada GPU (--rpc) NO guarda el modelo, solo ejecuta sus capas en VRAM. La red elige sola qué nodo orquesta (director) — nadie lo teclea — y ese baja el modelo y lo trocea entre todas. Un modelo de 100 GB entre 15 GPUs de 8 GB = nadie tiene el modelo entero. Cada GPU cobra lo suyo. Funciona entre casas distintas por el relay del VPS (aunque haya router/NAT).