AIBOX-9075 KIT Industrial Vision Edge Computing Kit

AIBOX-9075 KIT Industrial Vision Edge Computing Kit

$0.00
$0.00
Skip to product information
AIBOX-9075 KIT Industrial Vision Edge Computing Kit
  • AIBOX-9075 KIT Industrial Vision Edge Computing Kit
  • AIBOX-9075 KIT Industrial Vision Edge Computing Kit
  • AIBOX-9075 KIT Industrial Vision Edge Computing Kit
  • AIBOX-9075 KIT Industrial Vision Edge Computing Kit
  • AIBOX-9075 KIT Industrial Vision Edge Computing Kit
  • AIBOX-9075 KIT Industrial Vision Edge Computing Kit
AIBOX-9075 KIT Industrial Vision Edge Computing Kit

AIBOX-9075 KIT Industrial Vision Edge Computing Kit

$0.00
$0.00
Shipping calculated at checkout.

A 200 TOPS Qualcomm IQ-9075 edge AI kit for private LLM deployment and industrial applications.
  • American Express
  • Apple Pay
  • Google Pay
  • Mastercard
  • PayPal
  • Shop Pay
  • Union Pay
  • Visa
AIBOX-9075 KIT Edge Computing Kit

AIBOX-9075 KIT Edge Computing Kit

AIBOX-9075 KIT is powered by Qualcomm IQ-9075 processor, delivering up to 200 TOPS of peak computing power and 12TPS for 13B large model inference, supporting on-device private deployment of large models. Its octa-core CPU runs at up to 2.36GHz, making it suitable for high-load edge AI and multi-task concurrency. It integrates a security subsystem and four real-time cores. Built on the Qualcomm Linux software stack, it supports Ubuntu/Yocto systems and mainstream AI inference frameworks. With an industrial wide-temperature design, it offers GMSL2, CAN-FD, RS485, and optocoupler-isolated IO interfaces.

AIBOX-9075 KIT
200 TOPS NPU Computing Power

200 TOPS NPU Computing Power

Powered by Qualcomm IQ-9075 processor, it features dual Hexagon NPUs with peak sparse INT8 computing power of up to 200 TOPS. It supports CPU/GPU/NPU hardware co-acceleration, enabling on-device private deployment of large models and generative AI, with large model inference performance reaching 12TPS@13B, efficiently handling various complex AI computations and large model inference tasks.

Full-Stack Software Ecosystem Support

Full-Stack Software Ecosystem Support

Built on Qualcomm Linux software stack, it natively supports Ubuntu/Yocto systems and is compatible with mainstream AI inference frameworks such as TensorFlow, PyTorch, and ONNX. It supports on-device private deployment of large language models including Deepseek-R1, Gemma, Llama, Qwen, and Phi, as well as image generation models such as Stable Diffusion.

8-Channel GMSL2 Vision Capture Interfaces

8-Channel GMSL2 Vision Capture Interfaces

Equipped with 8 GMSL2 high-speed vision interfaces, it supports synchronized connection of high-definition cameras with a transmission distance of up to 20 meters. It offers strong anti-interference capability, stably adapting to complex industrial electromagnetic environments, ensuring millisecond-level synchronization of multiple image streams, and seamlessly supporting multi-camera scenarios.

Application Scenarios

Widely suitable for edge computing, private deployment of large models, industrial automation, intelligent surveillance, robotics, industrial vision inspection, intelligent security, intelligent driving, computer vision, retail automation, medical self-service terminals, in-vehicle multi-camera perception, smart city terminals, and other products and fields.

Edge Computing
Edge Computing
Private Deployment of Large Models
Private Deployment of Large Models
Industrial Automation
Industrial Automation
Smart Surveillance
Smart Surveillance
Robots
Robots
Industrial Camera
Industrial Camera

Interfaces

Interfaces

Specifications

AIBOX-9075 KIT (BASE)AIBOX-9075 KIT(PRO)
Basic Specifications SOC

Qualcomm IQ-9075

CPU

Qualcomm Kryo® Gen6 CPU: Octa-core 64-bit (8×Kryo Gold Prime), up to 2.36 GHz

MCU

Integrated subsystem with quad-core Cortex‑R52 CPU; each Cortex‑R52 CPU runs at up to 1.85 GHz, supporting independent boot via the OSPI interface

GPU

Adreno 663 GPU supports safe GPGPU compute, up to840MHz

· Graphics APIs: Vulkan 1.2, OpenGL ES 3.2

· Compute APIs: Vulkan 1.2, OpenCL 2.0 FP, Adreno NN Direct

ISP

Qualcomm Spectra 690 ISP Image Signal Processor, featuring 2× Image Front End (IFE) + 5× Lightweight Image Front End (IFE_L). Supports 24-bit HDR Bayer processing, lens distortion correction, advanced tone
mapping, offset correction, lens vignetting correction, dead pixel correction, directional scaling, color lookup table, color space conversion and noise reduction.

DPU

Dual Adreno DPU1199 supports image processing features including target scaler, exclusion rectangle extraction, inline rotation, 17×17×17 3D LUT (ViG/DSPP), HDR10 enhancement, wide gamut WCG, corner rounding, and CCCS fixed-point conversion. It also supports UBWC 4.0 and DSC v1.2 image compression technologies.

NPU

Dual Hexagon Tensor Processor integrating Qualcomm Hexagon DSP, clocked up to 1.42 GHz. It incorporates 4 Hexagon Vector Extension (HVX) and 2 Hexagon Matrix Extension (HMX) cores, delivering up to 100 TOPS (Dense INT8) / 200 TOPS (Sparse INT8), and achieves 22 token/s for Llama2-7B inference.

Codec

Video decoding: 1×8K@60fps, 2×8K@30fps, 4×4K@60fps, 8×4K@30fps, 16×1080p@60fps, 32×1080p@30fps AV1, H.264, H.265, VP9, MPEG2

Video encoding: 2×4K@60fps, 4×4K@30fps, 8×1080p@60fps, 16×1080p@30fps H.264, H.265, HEIF/HEIC

RAM

36GB LPDDR5 (ECC supported)

Storage

128GB UFS2.2

Storage expansion

1 × M.2 (PCIe 4.0 x4 NVMe 2280 SSD expandable)

OS

Ubuntu, Yocto Linux Software Stack

Software support

Supports private deployment of ultra-large parameter models under the Transformer architecture, including the Deepseek-R1 series, Gemma series, Llama series, Qwen series, Phi series and other large language models.

Supports private deployment of image generation models such as Stable Diffusion.

Supports the QNN AI inference framework, as well as multiple deep learning frameworks including TensorFlow, TensorFlow Lite, PyTorch, ONNX, Keras and Caffe.

Power

DC 12V/5A (5.5 × 2.1mm)

Power consumption

Normal: 8.4W(12V/700mA), Max: 24W(12V/2000mA), Min(Sleep): 1.08W(12V/90mA)

Normal: 12W(12V/1000mA), Max: 60W(12V/5000mA) , Min(Sleep): 1.08W(12V/90mA)

Dimension

91.40mm × 91.40mm × 54.33mm (with heat sink)

91.40mm × 102.10mm × 71.93mm (with heat sink)

Environment

Operating Temperature: -40℃ ~ 85℃, Storage Temperature: -40℃ ~ 90℃, Storage Humidity: 10% ~ 90%RH (non-condensing)

Interface Specifications Ethernet

2 × 2.5G Ethernet (2.5Gbps/RJ45)

Wireless network

Wi-Fi & Bluetooth: Supports Wi-Fi 6 and Bluetooth 5.2 (expandable via internal M.2 E-KEY)

4G/5G: Expandable via internal Mini PCIe

Video input

Not

8 × GMSL2 (2×4Pin Mini FAKRA)

Video output

1 × HD2.0 (4K@60Hz)

USB

2 × USB3.0 (Max: 1A), 1 × Type-C (Debug)

Button

1 × Power Button, 1 × Flash Button

Other interfaces

1 × SIM Card, 1 × FAN (2Pin-1.25mm)

1 × SIM Card, 1 × FAN (2Pin-1.25mm), 1 × Phoenix terminal block (36Pin, 3.5mm pitch): 2 × RS485, 2 × CAN-FD, 12 × Opto-isolated DI/DO

Customization

Firefly team provides hardware, software, turnkey and OEM/ODM customization services.

Hardware Solution Software Solution Turnkey Solution OEM/ODM Solution

Firefly is dedicated to delivering hardware-software-integrated intelligent solutions across diverse industries. Firefly is dedicated to delivering hardware-software-integrated intelligent solutions across diverse industries.

Contact Us

Onsite SupportOnsite Support

Email SupportEmail Support

Remote Video SupportRemote Video Support

Real-time SupportReal-time Support