Available Colors
Midnight Black
Arctic White
Space Gray
Technical Specifications
Enterprise-grade hardware engineered for AI workloads.
Dimensions
- Height
- 6 inches (152.4 mm)
- Width
- 4 inches (101.6 mm)
- Depth
- 1.2 inches (30.5 mm)
- Weight
- 450g (0.99 lbs)
Compute
- CPU
- ARM Cortex-A78AE 8-core @ 2.84 GHz
- GPU
- NVIDIA Jetson Orin NX 16GB
- NPU
- 100 TOPS AI Accelerator
- RAM
- 16GB LPDDR5 6400 MT/s
- Storage
- 256GB NVMe SSD
AI Performance
- INT8 Inference
- 100 TOPS
- FP16 Performance
- 25 TFLOPS
- Tokens/second
- 45-60 tokens/s (7B model)
- Max Context
- 128K tokens
Connectivity
- Ethernet
- 2.5 Gigabit
- Wi-Fi
- Wi-Fi 6E (802.11ax)
- Bluetooth
- 5.3 LE
- USB
- 2x USB-C 3.2, 1x USB-A 3.0
- HDMI
- HDMI 2.1 (4K60)
Power
- Input
- 12V DC / USB-C PD 65W
- Typical Load
- 25W
- Max Power
- 45W
- Idle Power
- 5W
Supported Models
Pre-installed with Thox.ai Coder, compatible with all Ollama models.
Recommended
Thox.ai Coder 7B
- Speed
- 55 tokens/s
- Quantization
- Q4_K_M
- Context
- 128K tokens
Thox.ai Coder 14B
- Speed
- 28 tokens/s
- Quantization
- Q4_K_M
- Context
- 64K tokens
Thox.ai Coder 32B
- Speed
- 12 tokens/s
- Quantization
- Q4_K_M
- Context
- 32K tokens
Llama 3.2 3B
- Speed
- 80 tokens/s
- Quantization
- Q8_0
- Context
- 128K tokens
Plus support for Mistral, CodeLlama, DeepSeek, and 100+ other Ollama models.
What's in the Box
Everything you need to get started.
- Thox.ai Edge Device
- 65W GaN USB-C Power Adapter
- USB-C to USB-C Cable (1m)
- Quick Start Guide
- Ethernet Cable (CAT6, 1m)
- Mounting Bracket Kit
- Thermal Pad Set
Frequently Asked Questions
Got questions? We've got answers.