Gateway Layer

• AI Gateway: Handles general AI inference tasks like CV, audio processing or sensor data analysis

• LLM Gateway: Manages the more resource intensive language model inference

Edge Network Layer

• Edge Devices: handle the actual computation

• Master Node: Manages orchestration, scheduling and control plane operations

Decentralized Layer

• DID: Essential for secure node authentication, reputation tracking and trust establishment.

• Smart Contracts: Critical for automated resource allocation, payment processing and SLA enforcement.

The rise of large language models (LLMs) has fundamentally changed how humans interact with machines. These models can understand and generate human like language, making conversations with AI feel more natural.

From writing and research to coding and customer support, LLMs are now helping people work, learn, and create in smarter, faster ways. They’ve turned machines into collaborators, not just tools. However, the current dominant model, cloud based AI inference, suffers from latency, privacy concerns, and scalability limitations.

iG3 proposes a new paradigm: a decentralized edge computing network powered by thousands of AI enabled devices across the globe, providing instant, private, and cost effective real time AI interaction.

These devices form the first inference layer, while high-power data centers with H100/H200 GPUs serve as the fallback for complex requests. Powered by a tokenized incentive system and DID integration on the peaq network, iG3 offers a robust infrastructure for education, entertainment, and productivity use cases.

As AI engineers and robotics enthusiasts, we encountered the same pain points that many developers, creators, and innovators face daily:

• Delays when speaking to AI assistants.

• Robots struggling to respond in real-time.

• Cloud models breaking immersion due to latency.

• High infrastructure costs to deliver low-latency AI at scale.

We've built robots that needed to understand humans but by the time the cloud responded, the moment was already lost. We've built prototypes that worked brilliantly in the lab but crumbled in the real world because latency made them feel dumb.

That's why we built iG3, not as a product, but as a solution to our own frustration.

We imagined a network where intelligence lived close to the user, not halfway around the world. Where devices could:

• Listen, think, and speak in real time.

• Run LLMs, vision models, and voice pipelines without relying on cloud APIs.

• Work together in a secure, decentralized mesh.

• Be owned by the people who run them and reward those who do.

We designed a hybrid system:

• M1 Devices act as intelligent gateways — capturing inputs, managing sessions, verifying identities.

• M1E specialize in inference — running vision, voice, and multimodal models at the edge.

• LLM Gateways provide fallback for complex tasks — tapping into powerful H100/H200 GPU clusters.

It’s a symphony of AI at the edge — fast, modular, and human-centric.

We didn’t stop at performance. We built the incentives to scale:

• A token system that rewards real contribution.

• A regional mining mechanism that encourages global participation.

• DID integration to anchor trust and verifiability.

This is more than infrastructure. This is a movement.

iG3 is for the builders. The tinkerers. The believers in better.

If you’ve ever shouted “Hey AI!” and waited too long for a response, you’ll understand why iG3 needs to exist.

How iG3 Solves Problems

The Latency Gap in Cloud AI

Cloud inference platforms often take several seconds to respond to voice or video prompts. In use cases like language tutoring, customer service, or gaming, this latency breaks immersion and utility.

Centralization Risks

The centralized nature of today’s AI platforms poses risks around control, surveillance, and censorship. Users must trust that their data is handled ethically.

Scalability and Cost

Hosting LLMs at scale in cloud infrastructure becomes economically unsustainable when applied to millions of daily users or devices.

M1 Device (Agent Node)

The M1 is the foundational unit of the iG3 Edge Network. Equipped with modest hardware (Intel N100 / ARM Cortex-A78 Octa-core), each M1 runs as a K3s Agent Node, responsible for:

• Hosting microservices (e.g., AI inference, data collection)

• Performing real-time tasks (e.g., audio/video processing)

• Communicating with Master Nodes for coordination

Master Node (Control Plane)

Deployed in a more robust environment (e.g., cloud, data center, or a high spec on prem node), the Master Node runs the K3s Server role:

• Controls scheduling, state management, and deployment logic.

• Maintains the cluster state for all connected M1 nodes.

• Integrates with the AI Gateway and LLM Gateway for service orchestration.

The Decentralized Infrastructure layer leverages blockchain technology to ensure transparency, fairness, and trustless coordination across the iG3 ecosystem. This layer powers the reward system, identity management, and device licensing via the peaq network.

Blockchain:

• Built on the peaq network, optimized for DePIN use cases.

• Handles:

  • DID Registration: Secure, decentralized identity for all devices.

  • Proof of Uptime: Verifiable uptime reporting to determine reward eligibility.

  • Reward Issuance: Automates $iG3 token payouts based on performance and availability.

  • NFT-Based Device Licenses: Each edge device is issued a tradable license NFT to verify its legitimacy and tier.

Smart Contracts:

• Uptime & Location Proofs: Ensures devices are active and geographically distributed.

• Staking Mechanism: Allows device owners to stake tokens for premium access or higher-tier rewards.

• Reward Formula:

  Copy

  Base Rate + Performance Bonus + Regional Weighting

  • Base: Guaranteed minimum.

  • Performance: Based on task completion, latency, and accuracy.

  • Region Weight: Encourages deployment in underrepresented or high-demand areas.

Token Incentivization:

• $iG3 Token Emission:

  • Distributed to edge operators based on real-time metrics recorded on-chain.

  • Designed to encourage uptime, availability, and AI task contribution.

  • Optional DAO-based governance for reward model updates and economic adjustments.

The total supply will be 39,000,000,000 tokens, distributed as follows:

Disclaimer: The tokenomics outlined in this document are subject to change as part of ongoing efforts to optimize and improve the project. Any modifications will be made with the intention of enhancing the ecosystem's sustainability, usability, and long-term value for all stakeholders.

• $iG3 acts as the primary currency within the iGam3 ecosystem

• Enables transactions between users, device owners and builders

• Supports iGam3’s core business models, including AI applications, AI infrastructure, and decentralized compute services

• Drives demand as users compensate providers of compute and services with iG3

AI Gateway (Orchestration Layer)

The AI Gateway acts as the central brain of the iG3 Edge Network. It manages all device interactions, workload assignments, and dynamic routing. Every edge device connects through this gateway to receive tasks, report results, and maintain secure identity verification.

Key Responsibilities:

• Device Registration & DID Verification: Each device is authenticated using Decentralized Identifiers (DID) on the peaq network.

• Workload Distribution: Distributes AI inference tasks to the most suitable nodes, preferring edge devices first and falling back to the cloud if needed.

• Task Queueing & Retry: Ensures fault tolerance with automatic re-queuing of failed jobs.

• Topology-Aware Load Balancing: Routes tasks based on proximity, device capability, and current load to optimize performance.

• Edge Model Discovery: Detects which models are available on which edge nodes for efficient dispatching.

Tech Stack:

• Kubernetes for service orchestration and mesh networking.

• Kafka as an event bus for task scheduling and status updates.

• gRPC APIs for high performance communication between services.

• Pub/Sub System to stream results and updates back to users and dashboards.

LLM Gateway

The LLM Gateway specializes in handling natural language tasks and large model interactions. It abstracts away model complexity and provides a streamlined interface for edge users to interact with LLMs in real time whether from a desktop client or a Telegram bot.

Key Responsibilities:

• Token Based Authentication: Secures access using wallet signatures or DID verification.

• Text Generation & Chat Handling: Receives prompts and routes them to the most appropriate model.

• Model Sharding & Orchestration: Supports parallelism across multiple GPUs or devices for scalability.

• Local Edge or Cloud Inference: Automatically selects between lightweight edge LLMs or cloud-hosted large models (e.g., H100-backed) depending on complexity and urgency.

Tech Stack:

• LiteLLM for API compatibility with major LLMs and simplified routing.

• vLLM / NVIDIA Triton / Text generation webui for efficient model hosting and scaling.

• Faiss / Qdrant to support retrieval-augmented generation (RAG) pipelines using vector search.

• Redis for caching frequent responses and reducing redundant compute.

• Billing & Metering Hooks to track usage and apply token-based pricing models.

When converting xG3 to iG3, users can choose between three unlock periods, each offering different conversion rates and burn percentages.

Unlock Period

• 15 Days:

  • Conversion Rate: 1 xG3 = 0.3 iG3 (30%)

  • Burn Rate: 70% of xG3 tokens are burned.

• 60 Days:

  • Conversion Rate: 1 xG3 = 0.6 iG3 (60%)

  • Burn Rate: 40% of xG3 tokens are burned.

• 90 Days:

  • Conversion Rate: 1 xG3 = 1 iG3 (100%)

  • Burn Rate: No tokens are burned.

Unlock and Access iG3

• iG3 tokens will be available after the selected unlock period:

  • 15 Days, 60 Days, or 90 Days.

• Once unlocked, the tokens will be available for use in your wallet.

The Edge Node Layer forms the foundation of the iG3 network, composed of distributed devices that run AI workloads close to users. These devices process real-time interactions, reduce latency, and preserve privacy by minimizing cloud dependency.

Key Capabilities:

• Real-time Audio I/O: Supports speech-to-text (STT) and text-to-speech (TTS) locally for instant voice interaction.

• Local Inference: Runs lightweight AI models such as quantized LLMs, Whisper.cpp, and compact TTS engines directly on-device.

• On-Device Task Execution: Handles specialized tasks like object detection, surveillance, and sensor data classification.

• Local Identity Management: Manages decentralized identifiers (DIDs) for secure and verifiable identity.

• Status Reporting: Periodically sends heartbeats, performance stats, and usage metrics to the AI Gateway.

Software Stack:

• Dockerized Microservices: Modular services for LLMs, audio processing, and task handlers.

• K3s (Lightweight Kubernetes): Orchestrates containerized services efficiently on resource-constrained hardware.

• gRPC or WebSocket: Enables fast and secure real-time communication with the AI Gateway.

• Edge Agent Daemon: A lightweight background service that handles device coordination, task reception, and model updates.

The iG3 token reward system is designed to encourage high performance, distributed, and honest behavior across edge device operators.

• BaseRate: Fixed reward baseline

• UptimeFactor: Ratio of uptime per 24h period

• TaskFactor: Measures the volume of successful AI tasks

• DensityBoost: Encourages operators to scale device ownership while ensuring fairness

To ensure fair distribution across the globe and prevent over-concentration, iG3 allocates a fixed reward pool per region based on the following criteria:

• Baseline Allocation: Each region (e.g., North America, Southeast Asia, Europe) receives a base share (e.g., 0.5% of total monthly rewards).

• Population Weighting: Adjust reward weight proportional to user base size or active devices in each region.

• Performance Bonus: If a region achieves > 95% average uptime or > 80% device activation, it receives a temporary bonus allocation for the following epoch.

Reward weights are reviewed and updated every 30-day epoch.

What is the M1?

The M1 Edge Device is designed to bring powerful AI to the edge. It provides a compact, energy efficient, and high performance solution for real time AI applications.

The M1 is the foundation of iG3, our decentralized edge network that enables natural conversation with AI models, visual AI enhancements, and real world interactions, all while keeping latency ultra-low and data private.

• Edge AI Processing: Run speech recognition, real-time video analytics, and AI inference locally without relying on cloud servers.

• Low Latency: M1 minimizes response times by processing directly at the source, critical for real-time interactions.

• Privacy-Preserving: With no need to send sensitive data to external servers, users maintain full control of their information.

• Energy Efficient: Powered by Intel N100, the device delivers solid performance while consuming minimal energy.

• Plug-and-Play: Simple setup. Auto-connect to our iG3 network and start contributing right away.

iGam3 is built on a foundation of cutting-edge hardware technologies

• Chip | Intel Alder Lake N100 Gen 12th Processor | hybrid architecture, decent performance for edge AI tasks, energy efficiency, and modern connectivity options.

• Graphic | Intel UHD Graphics 24 EUs (Alder Lake) 4K | improved performance for gaming, multimedia, and AI models.

• SSD | M.2 228 PCI Gen 4x4 NVMe 512GB | high-speed data transfer rates and enhanced storage performance.

• Memory | 16GB DDR4 3200 | ample memory capacity and fast data transfer speeds, smooth multitasking and efficient performance.

iGam3 is highly energy-efficient.

The device typically consumes between 9 and 15 watts per hour, with a maximum power draw of 15 watts when operating at full theoretical capacity. This low power consumption makes the iGam3 M1 highly cost-effective to run. For context, here’s a comparison of the average daily electricity costs for operating an edge device in different countries.

Setup FAQs

1. Open Your Web3 Wallet Ensure you're logged into the wallet where you want to add the $xG3 token.

2. Navigate to “Import Tokens”

   • Select “Import tokens”

   • Choose “Custom token”

3. Enter the Contract Address

   • Paste the following contract address: 0x15b07Fa1734C5118b158d559FB102B11F1cC16A0

4. Confirm Token Details

   • Token Symbol: xG3

   • Token Decimal: 18

5. Complete the Import

   • Click “Next”

   • Click “Import”

You should now see your $xG3 token balance displayed in your wallet.

You can do similar steps to add $iG3 balance to your wallet, just change the contract address to: 0xc3AEc0C2A21F62d75BEec655B33836cdED370d7d

Step 1: Download the iGam3 Mobile App

Step 2: Connect to Your iGam3 M1

1. Open the iGam3 Mobile App and wait for 10 seconds.

2. Scan the QR code displayed on your iGam3 M1 device screen to establish a connection.

Step 3: Set Up Wallet Access

Choose one of the following wallet options to connect:

• Wallet apps: Metamask, Trust Wallet, Gate Wallet, Binance Wallet, etc.

• Web Wallet: Use this option for browser-based wallet access.

Step 4: Monitor and Manage

Once connected, you can monitor your iGam3 M1 device’s performance and track your earnings directly within the app.

Q4/2024

• Launch the first batch of 2,000 iGam3 M1 Devices.

• Introduce the iGam3 Edge Mobile App.

• Initial support for LLMs.

• Release iGPT, the first Large Language Model (LLM) on the Edge Network.

• Begin R&D for the AI Agents Framework on Edge Network

Q1/2025

• List tokens on a Tier 2 centralized exchange (CEX).

• Expand to 10,000 iGam3 M1 Devices.

• Introduce the AI Agents Framework on Edge Network.

• Launch iG3 OS and its accompanying App Store.

• Integrate iGam3 M1 Devices with Layer 2 blockchain.

Q2/2025

• List tokens on a Tier 1 centralized exchange (CEX).

• Incorporate Zero-Knowledge (ZK) technology into the Edge Network.

• Launch the ZK Node Sale.

• Begin R&D for the iGam3 M2 Devices.

• Initiate the Super Grant Program to support AI and Robot developers.

Q3/2025

• Launch the first batch of 1,000 iGam3 M2 Devices.

• Secure additional Tier 2 CEX listings for tokens.

• Focus on B2B integration to expand business partnerships.

The iGam3 device comes with a One-Year Limited Warranty, designed to give you peace of mind and protect against any potential defects in materials or workmanship. This warranty covers the device for a period of one year from the date of purchase, ensuring that your iGam3 operates as intended under normal usage conditions.

What the Warranty Covers:

• Hardware Defects: Any issues caused by defects in materials or manufacturing that affect the performance or usability of the device.

• Repair or Replacement: During the warranty period, if your iGam3 experiences a covered defect, we will repair the device or, if necessary, replace it at no additional cost to you.

What the Warranty Does Not Cover:

• Accidental Damage: Any damage resulting from accidents, misuse, or neglect is not covered by this warranty.

• Unauthorized Modifications or Repairs: Repairs or modifications carried out by unauthorized service providers or individuals void the warranty.

• Wear and Tear: Normal wear and tear, including cosmetic damages that do not affect the device’s functionality, is not covered.

How to Claim Warranty Service:

If you encounter an issue, simply contact our customer support team with proof of purchase and details of the issue. We’ll guide you through the warranty process and ensure your device is back in working order as quickly as possible.

This warranty is limited to the original purchaser and may have specific exclusions or limitations depending on your country. Be sure to review the full warranty terms provided with your device for complete details.

Meet the team members behind the success of iGam3 and learn more about their roles and responsibilities.

1. Bit OG

   • Role: Founder & CEO

2. 0xGP

   • Role: CTO

3. Jenny Lee

   • Role: COO

4. Javier Gonzalez

   • Role: Head of Ecosystem

5. DreammywOw

   • Role: Head of CM (Community Management)

6. Sander Gortjes

   • Role: Advisor from HELLO Labs

7. Scott Foo:

   • Role: Advisor from Orbital Beam & CEO DePIN Daily

Each team member has a unique skill set that drives the innovation and growth of iG3. Let me know if you need more elaboration on any member or their responsibilities!

If you have any questions or concerns, please contact us via:

• Email [email protected]