MagStack™ Clustering
Revolutionary magnetic stacking technology for distributed AI inference
Proprietary Technology
This documentation describes proprietary trade secrets of THOX.ai LLC. Unauthorized reproduction, implementation, or reverse engineering is strictly prohibited.
MagStack™ Technology
Proprietary Technology | Trade Secret
Revolutionary magnetic stacking technology that enables multiple THOX.ai devices to combine RAM and compute power for running larger AI models.
Stack More. Compute More.
How MagStack™ Works
1. Physical Stacking
Simply place THOX.ai devices on top of each other. The powerful neodymium magnets automatically align the devices with sub-millimeter precision. No cables required.
2. Auto-Discovery
Automatic device discovery and Hall effect sensors detect the connection. Devices exchange capabilities and form a cluster via mDNS within ~10 seconds.
3. Leader Election
The cluster automatically elects a leader using a deterministic algorithm. Priority: external power → highest battery → lowest UUID.
4. Distributed Inference
AI models are partitioned using pipeline parallelism. Each device processes specific layers, with activations flowing via high-speed link.
The Stacking Process
When you stack two THOX.ai devices, a precise 5-step sequence automatically forms a compute cluster:
Step A: Approach Detection
As devices approach within 30mm, automatic device discovery detects each other. This triggers the handshake sequence before physical contact.
Range: 30mm detection, 4mm handshake initiation
Step B: Device Handshake
At 4mm range, devices exchange critical information via automatic discovery:
- Device UUID and firmware version
- Available RAM and GPU cores
- Cluster capabilities and current state
- Security certificates for authentication
Step C: Magnetic Alignment
8x powerful neodymium magnets (4 per surface) with alternating polarity guide the devices into perfect alignment. Self-centering corrects up to 5mm offset.
Step D: Physical Connection
The high-speed data interconnect engages, establishing:
- High-speed USB 3.2 Gen 2 data link for model layer activations
- USB Power Delivery up to 100W passthrough
- I2C bus for power negotiation and telemetry
High-speed interconnect with precision spring-loaded contacts
Step E: Cluster Active
The software layer completes cluster formation:
- Leader elected (external power → highest capacity → lowest UUID)
- AI models automatically partitioned across available memory
- Health monitoring begins (heartbeat every 2 seconds)
- Cluster ready for inference in ~10 seconds
Distributed AI Inference
Pipeline Parallelism
MagStack uses pipeline parallelism to distribute large AI models across devices. Each device processes specific layers, with intermediate activations flowing between devices via the high-speed data interconnect.
# Example: 70B model on 2-device stack
70B Model (Q4 quantized)
├─ Layers 0-16 (35GB) → Device 1 (16GB RAM)
└─ Layers 17-32 (35GB) → Device 2 (16GB RAM)
# Data flow
INPUT → Device 1 → [High-Speed Link] → Device 2 → OUTPUT
Token Latency
~200ms
per token (70B model)
Generation Speed
5-8 tok/s
70B model on 2x stack
Cluster Efficiency
50-60%
sub-linear scaling (2 devices)
Cluster Configurations
| Configuration | Devices | Combined Memory | Max Model | Speed |
|---|---|---|---|---|
| Single Device | 1x | 16GB | 32B | 20-72 tok/s |
| 2x Stack | 2x | 32GB | 70B | 25-45 tok/s |
| 4x Stack | 4x | 64GB | 100B+ | 15-30 tok/s |
| 8x Stack | 8x | 128GB | 200B+ | 10-20 tok/s |
Recommended Models
2-Device Stack (32GB)
- thox-cluster-nano - 30B, 1M context (Recommended)
- thox-cluster-70b - 70B parameters
4-Device Stack (64GB)
- thox-cluster-100b - 100B+ parameters
8-Device Stack (128GB)
- thox-cluster-200b - 200B+ frontier model
Special: 1M Context
The thox-cluster-nano model offers 1 million token context for processing entire codebases in a single session.
Cluster CLI Commands
# Check cluster status
$ clusterctl status
# View cluster topology
$ clusterctl topology
# Load a cluster model
$ clusterctl load thox-cluster-nano
# Check recommended model
$ clusterctl recommend
# Monitor real-time metrics
$ clusterctl monitor --realtime
Key Features
Magnetic Alignment
Powerful magnets ensure perfect alignment every time you stack.
Auto-Discovery
Devices automatically discover each other and form clusters when stacked.
Combined Resources
Stack 2-8 devices to aggregate memory and compute for larger AI models.
Instant Scaling
Automatic cluster coordination ensures seamless scaling.
Precision Design
Self-centering design ensures stable stacking with no lateral movement.
Hot-Swappable
Add or remove devices from the stack without interrupting the cluster.
Technical Specifications
- alignment
- Magnetic self-centering
- discovery
- Automatic device discovery
- data Link
- High-speed data interconnect
- power Passthrough
- Passthrough power delivery
- interconnect
- Wi-Fi 6
- max Stack Height
- 8 devices
- cluster Formation
- Automatic, no configuration needed
Intellectual Property Notice
MagStack™ is a trademark of THOX.ai LLC.
Patent Protection
The MagStack™ magnetic stacking interface system is proprietary technology and constitutes valuable trade secrets of THOX.ai LLC.
Prohibition Notice
NOTICE: Unauthorized manufacture, use, sale, offer for sale, or importation of devices or systems implementing MagStack™ technology, or any substantially similar technology, is strictly prohibited and may result in civil liability and criminal prosecution. Reverse engineering, disassembly, or decompilation of MagStack™ hardware or software is expressly forbidden.
The technical specifications disclosed herein are provided for informational purposes only and do not constitute permission to implement or reproduce any protected technology. All rights reserved.
© 2026 THOX.ai LLC. All rights reserved.
CONFIDENTIAL AND PROPRIETARY INFORMATION
This documentation is provided for informational and operational purposes only. The specifications and technical details herein are subject to change without notice. THOX.ai LLC reserves all rights in the technologies, methods, and implementations described.
Nothing in this documentation shall be construed as granting any license or right to use any patent, trademark, trade secret, or other intellectual property right of THOX.ai LLC, except as expressly provided in a written agreement.
Patent Protection
The MagStack™ magnetic stacking interface technology is proprietary technology of THOX.ai LLC, protected by trade secrets and intellectual property laws....
Reverse Engineering Prohibited
You may not reverse engineer, disassemble, decompile, decode, or otherwise attempt to derive the source code, algorithms, data structures, or underlying ideas of any THOX.ai hardwa...
THOX.ai™, ThoxOS™, MagStack™, MeshStack™, and the THOX.ai logo are trademarks or registered trademarks of THOX.ai LLC in the United States and other countries. WireGuard® is a registered trademark of Jason A. Donenfeld.
All other trademarks are the property of their respective owners.
© 2026 THOX.ai LLC. All Rights Reserved.