AI HARDWARE DATABASE
AI Hardware Directory · Page 19 of 21 (183 Verified Devices)
PAGINATED HARDWARE DIRECTORY · PAGE 19 OF 21

AI Hardware Specification Database

Showing devices 163–171 of 183 lab-benchmarked physical AI products.

EngineAI Pre-Order
Embodied AI & Robotics · 170cm 55kg · 32-DoF 330N·m · Natural RL Gait

EngineAI SE01 170cm 32-DoF 330N·m Aerospace-Aluminum & End-to-End Natural-Gait Bipedal Humanoid

170cm, 55kg full-size bipedal humanoid robot CNC-machined from aerospace-grade aluminum alloy with 32 total degrees of freedom, hybrid harmonic + planetary joint actuators (up to 330 N·m peak torque), dual NVIDIA Jetson Orin NX + Intel x86 compute, and an end-to-end reinforcement-learned controller delivering straight-knee heel-to-toe human stride at 2.0 m/s.

Silicon / SoC Heterogeneous Onboard Compute: Dual NVIDIA Jetson Orin NX AI Modules + High-Frequency Intel x86 Real-Time Host
AI Model End-to-End Deep Reinforcement Learning & Imitation-Prior Sim-to-Real Gait Network (2.0 m/s Heel-to-Toe Stride)
Weight 55.0kg Ultralight Full-Scale Mass / 170cm Height (High-Strength CNC-Machined Aerospace Aluminum Exoskeleton)
Battery Quick-Release High-Discharge Torso Lithium Battery Pack (~2 Hours Continuous Dynamic Walking & Squatting)
Orange Pi In Stock
Edge Compute & DevKits · 89×56mm RK3588 · LPDDR5 · 4K60 HDMI-In + Wi-Fi 6E

Orange Pi 5 Ultra (89×56mm RK3588 6-TOPS NPU, 16GB LPDDR5, 4K60 HDMI-In, Wi-Fi 6E & PCIe 3.0 x4 SBC)

60.5-gram (89×56mm) credit-card-class single-board computer packing the full 8nm Rockchip RK3588 SoC (8-core Cortex-A76/A55 + 6-TOPS NPU), up to 16GB LPDDR5 RAM, unsplit M.2 2280 PCIe 3.0 x4 NVMe storage, full-size HDMI 2.0 4K60 video input + HDMI 2.1 8K60 output, onboard Wi-Fi 6E / BT 5.3, and 2.5GbE.

Silicon / SoC Rockchip RK3588 (8nm Octa-Core: 4× Cortex-A76 @ 2.4GHz + 4× Cortex-A55 @ 1.8GHz + ARM Mali-G610 MP4 GPU)
AI Model 6.0 TOPS Embedded 3-Core NPU (INT4/INT8/INT16/FP16 Hybrid Compute via RKNN-LLM & RKNN-Toolkit2)
Weight 60.5g (89 × 56mm Ultra-Compact 1.6mm PCB Footprint Ideal for UAV Gimbals & Portable AI Appliances)
Battery 5V/5A USB Type-C Power Input (~4W Idle / ~11W Full NPU + 8-Core Load)
M5Stack In Stock
Edge Compute & DevKits · 23.6g AX630C · 12.8 INT4 TOPS · ~3W StackFlow

M5Stack LLM630 Compute Kit (23.6g AXERA AX630C 12.8-TOPS INT4 Offline Edge-LLM & ESP32-C6 DevKit)

23.6-gram (90.3×31.6×12.0mm) ~3W fanless offline LLM and vision compute kit powered by the AXERA AX630C SoC (3.2 TOPS INT8 / 12.8 TOPS INT4 Transformer NPU), 4GB LPDDR4 (2GB dedicated to NPU), 32GB eMMC 5.1, onboard ESP32-C6 Wi-Fi 6 coprocessor, Gigabit Ethernet, BMI270 IMU, duplex audio, and M5 StackFlow plug-and-play AI.

Silicon / SoC AXERA AX630C Edge AI SoC (Dual-Core ARM Cortex-A53 @ 1.2GHz) + Onboard ESP32-C6 Wi-Fi 6 Companion MCU
AI Model 3.2 TOPS @ INT8 / 12.8 TOPS @ INT4 Mixed-Precision NPU Running StackFlow (Qwen2.5, Llama-3.2-1B, Whisper, MeloTTS, YOLO11)
Weight 23.6g Bare Compute Kit (90.3 × 31.6 × 12.0mm Thumb-Stick Footprint; ~2.5W–3.5W Passive Fanless Operation)
Battery 5V USB Type-C Power Input (Dual USB-C OTG & Debug Ports + Ultra-Low ~3W Envelope for Portable LiPo Packs)
Snap Inc. In Stock
AI Smart Glasses · 226g Standalone · 46° LCoS Waveguide · Dual SoC

Snap Spectacles (5th Gen / Snap OS) 226g Dual-Snapdragon 46°-FOV LCoS Waveguide Standalone AR Glasses

226-gram untethered standalone see-through augmented-reality spatial computer powered by dual Qualcomm Snapdragon processors, custom Liquid-Crystal-on-Silicon (LCoS) micro-projectors with stereo waveguides (46° diagonal FOV, 37 pixels per degree, auto-tinting lenses), 4 Snap Spatial Engine 6DoF & hand-tracking cameras, and Snap OS multimodal OpenAI/Gemini AI Lenses.

Silicon / SoC Dual Qualcomm Snapdragon Titanium-Vapor-Cooled Spatial SoCs (Split Across Left & Right Temples for Thermal Balance)
AI Model Snap OS 2.0 Spatial Engine + Multimodal AI Lenses Integrating OpenAI GPT-4o, Google Gemini Vision & On-Device ML
Weight 226.0g Self-Contained Untethered Chassis w/ Automatic Photo-Electrochromic Indoor/Outdoor Lens Tinting
Battery Up to 45 Minutes Standalone Untethered AR Execution (Continuous Extended Sessions via USB-C Pocket Power Bank)
HTC VIVE In Stock
AI Smart Glasses · 48.8g ZEISS Frame · AR1 Gen 1 · Gemini + GPT AI

HTC VIVE Eagle 48.8g Snapdragon AR1, ZEISS UV400, 12MP Camera & Multi-LLM Voice AI Smart Glasses

48.8-gram display-free everyday AI camera and open-ear audio smart glasses crafted with ZEISS UV400 lenses, Qualcomm Snapdragon AR1 Gen 1 silicon (4GB RAM + 32GB storage), a 12MP ultrawide first-person camera, 4-microphone beamforming array, Wi-Fi 6E, 10-minute 50% magnetic fast-charging, and VIVE AI routing across Google Gemini and OpenAI ChatGPT.

Silicon / SoC Qualcomm Snapdragon AR1 Gen 1 Dedicated Eyewear SoC Paired w/ 4GB LPDDR RAM + 32GB Onboard Flash Storage
AI Model Hands-Free 'Hey VIVE' Multi-Model AI Assistant Supporting Google Gemini & OpenAI ChatGPT Live Translation & Visual Q&A
Weight 48.8g w/ Lenses (~48.5g Pantos / ~49.0g Square; 42.8g Bare Frame, IP54 Dust & Splash Resistant)
Battery 235mAh Internal Battery (>36h Standby / 4.5h Music / >3h Calls; Magnetic Fast-Charge 1% to 50% in 10 Minutes)
Neurable × Master & Dynamic In Stock
AI Wearables & Audio · 294g BCI Audio · 12-Ch Ear-Pad EEG · 22h Battery

Neurable × Master & Dynamic MW75 Neuro LT 294g 12-Channel Dry-EEG BCI & 40mm Beryllium ANC Headphones

294-gram (12% lighter second-gen) brain-computer interface wireless ANC headphones embedding 12-channel True-DC-coupled soft-fabric dry EEG sensors directly inside magnetic replaceable ear cushions alongside 40mm Beryllium acoustic drivers, adaptive ANC, 16-hour offline EEG caching, and 22-hour continuous cognitive focus & burnout AI tracking.

Silicon / SoC Low-Noise 12-Channel True-DC-Coupled Biopotential AFE (0–131 Hz EEG Bandwidth) + Qualcomm aptX Adaptive Bluetooth DSP
AI Model Neurable Brain-Computer Interface AI (Real-Time Deep-Focus Score, Cognitive Snapshot, Brain Age & Burnout Break Prompts)
Weight 294.0g Ergonomic LT Architecture (44g / 12% Lighter than Original 338g MW75 Neuro w/ Magnetic Snap-On EEG Ear Pads)
Battery Up to 22 Hours Continuous Active EEG + ANC Playback (Up to 32h Audio-Only; 16h On-Device Offline EEG Memory Buffer)
Earable Neuroscience In Stock
AI Wearables & Audio · 75g Sleep Band · EEG+EOG+EMG · Bone Conduction

Earable Neuroscience FRENZ Brainband 75g 7-in-1 EEG/EOG/EMG & Bone-Conduction Closed-Loop Sleep AI Band

75-gram medical-grade flexible neuro-sleep headband integrating a 7-in-1 polysomnography sensor suite (dry forehead EEG, eye-movement EOG, facial micro-muscle EMG, optical PPG SpO2/HRV, and 3D IMU) with dual pressure-proof hanging bone-conduction speakers for real-time closed-loop slow-wave pink-noise and CBT-i acoustic stimulation.

Silicon / SoC Multi-Channel Mixed-Signal Polysomnography AFE (EEG/EOG/EMG + Optical PPG) & Low-Latency BLE Audio SoC
AI Model Closed-Loop Real-Time Sleep-Stage Classifier (~88%+ PSG Concordance) Driving Dynamic Pink-Noise, Binaural & CBT-i Audio
Weight 75.0g Flexible Side-Sleeper Ergonomic Band w/ Patented Non-In-Ear Hanging Bone-Conduction Acoustic Chambers
Battery Up to 8–10 Hours Continuous Overnight Biopotential & Bone-Conduction Audio Runtime via Magnetic Charging Dock
Hengbot In Stock
Desktop & Companion · 1.0kg Aluminum · 14-DoF Neurocore · 5-TOPS LLM

Hengbot Sirius 1.0kg 14-DoF Neurocore-Actuator, Aerospace-Aluminum & 5-TOPS Multimodal-LLM Robot Dog

1.0-kilogram (~250×130×250mm) CNC aerospace-aluminum biomimetic quadruped companion robot driven by 14 proprietary high-backdrivability Neurocore actuators (12 leg DoF + 2-DoF articulated head/neck), a 5-TOPS Linux edge AI SoC, an 8MP wide-angle vision camera, beamforming mics, and open-source Python/C++/drag-and-drop multimodal LLM persona customization.

Silicon / SoC 5-TOPS Embedded Linux Edge AI Vision Processor (RDK X3 Architecture) + Dedicated Real-Time Joint-Control MCU
AI Model Onboard Visual Gesture/Face Recognition + Multimodal Cloud/Local LLM Agent Translating Voice into 1,000+ Bionic Motions
Weight 1,000g (1.0kg / ~250 × 130 × 250mm) All-Metal CNC Aerospace-Grade Aluminum-Alloy Exoskeleton
Battery 2,250mAh High-Rate Rechargeable Lithium Pack (40–60 Mins Dynamic Agile Gait / 50–60 Mins Fast USB-C Recharge)
Luwu × Elecfreaks In Stock
Desktop & Companion · 560g Wheel-Biped · FOC Hub + CM4 · 2.0" IPS + LLM

Luwu Intelligence × Elecfreaks XGO-Rider (CM4) 560g FOC Wheel-Legged Self-Balancing Linux AI Desktop Bot

560-gram (135×118×116–158mm) desktop wheel-legged self-balancing robot combining outer-rotor FOC brushless hub motors and 4.5 kg·cm magnetic-encoder metal leg servos with a Raspberry Pi Compute Module 4 (CM4) + ESP32 dual-brain stack, 5MP OV5647 camera, 2.0-inch IPS expression screen, and open-source Python/ROS/ChatGPT multimodal interaction.

Silicon / SoC Dual-Controller Architecture: Raspberry Pi Compute Module 4 (Quad-Core Cortex-A72, 2GB RAM, 32GB SD) + ESP32 Balance MCU
AI Model Open-Source Python, ROS & Blockly Stack w/ OpenCV/MediaPipe Vision Tracking + ChatGPT Multimodal Voice-Vision Agent
Weight 560.0g Net Machine Mass (135 × 118 × 116–158mm Variable-Height 1mm Aluminum-Alloy + Carbon-Fiber Frame)
Battery Integrated 2S Rechargeable Lithium Battery Pack Delivering ~2 Hours Continuous Self-Balancing & AI Runtime (USB-C)