APLUX

High-compute industrial intelligent module

Rhino Core IQ9

A powerful core for local data and real-time tasks

A Dragonwing IQ-9075 intelligent module with an octa-core application processor, quad-core real-time subsystem and up to 100 TOPS (INT8, dense), providing a core platform for local AI, industrial terminals and robotics projects.

Rhino Core IQ9 angled view

100 TOPS

Maximum AI performance (INT8, dense)

36 GB

Standard LPDDR5 configuration

Quad-core R52

Real-time subsystem

65 × 65 mm

Package dimensions from the product brief

A powerful core for local data and real-time tasks

Match the compute platform to your device tasks, models, peripherals and product form factor.

Application computing and a real-time subsystem

Octa-core Kryo Gen 6 and quad-core Cortex-R52 provide heterogeneous resources for model inference, business applications and real-time workloads.

Local models and data processing

100 TOPS of dense compute and 36 GB LPDDR5 provide a basis for local model deployment. Assess model size against quantization, context length and runtime environment.

Multicamera and high-speed expansion

The platform provides CSI, PCIe Gen4, USB and display resources; confirm routing and electrical definitions against the specific module design documentation.

Integration into customer devices

Validate storage, networking and local AI on a custom carrier. Obtain module pin assignments, power sequencing and electrical documentation before production design.

Explore integration paths for real-world tasks

Choose device workloads and integration paths based on platform capabilities and this model's interfaces.

Qualcomm Dragonwing IQ-9075

Handle more complex edge AI tasks

Multimodal understandingEdge computingHigh-speed data links
Up to 100 TOPS(INT8, dense)Platform-rated peak; validate performance for your workload
Illustrative industrial controller

Industrial controller

Combine complex models, device data processing and companion industrial interfaces to integrate local compute into field control systems.

Platform fit
Connect more complex vision and device data analysis to higher-level intelligence in industrial systems.
Module integration
Expose CAN FD / UART resources through the carrier with transceivers; implement networking through SGMII.
Device dataModel analyticsSystem coordination
View interfaces and integration
Illustrative drone controller

Drone controller

Handle airborne perception and higher-level task inference, connecting to an external flight controller through a compatible carrier and communication link.

Platform fit
Use local models to process airborne vision and task information, returning perception results to the flight controller.
Module integration
Match cameras, flight-controller communication and airborne power on the carrier; the companion system handles flight control and safety.
Onboard perceptionTask inferenceFlight controller coordination
View interfaces and integration
Illustrative robot controller

Robot controller

Provide local compute for robot perception, multimodal understanding and task planning; a companion control system coordinates motion control.

Platform fit
Provide edge compute for robot perception, multimodal understanding and task planning.
Module integration
Connect sensors and controllers over CSI, PCIe, USB and networking; verify carrier pin assignments and electrical requirements first.
Sensor inputMultimodal understandingTask planning
View interfaces and integration
Illustrative AI NAS

AI NAS

Connect storage media, network access and local models to make files, photos and knowledge easier to retrieve and use.

Platform fit
Run retrieval and content understanding close to private data, extending storage nodes into local intelligent services.
Module integration
Use PCIe and networking for storage carriers; plan NVMe / SATA controllers, drive bays and cooling separately.
Private contentLocal retrievalIntelligent access
View interfaces and integration

Device images illustrate application directions; peripherals, enclosure and software require project-specific integration. Modules require a carrier; platform resources are not equivalent to physically exposed device interfaces.

Rhino Core IQ9 specifications

Configurations below follow the high-compute industrial intelligent module documentation. Module capabilities and physically exposed device interfaces are distinguished.

Compute and storage

Rhino Core IQ9 · Compute and storage
Compute platformQualcomm Dragonwing IQ-9075
Chip identifierQCS9075M
Process4 nm
CPUOcta-core Qualcomm Kryo Gen 6, up to 2.36 GHz
NPUQualcomm Hexagon
AI performance (INT8, dense)Up to 100 TOPS(INT8, dense)
GPUQualcomm Adreno 663,800 MHz
Real-time subsystem4 × Cortex-R52, platform maximum 1.85 GHz
Memory36 GB LPDDR5 (standard configuration in the current product brief)
StorageUFS 3.1 / eMMC; capacity configured for the project

AI figures are platform-rated peaks. Dense, sparse and FP16 figures are listed separately; actual performance depends on the model, precision, software and cooling. Input power ratings do not represent total board consumption. Accessories and system images depend on the delivered configuration.

Product configuration and integration notes

Product briefs are currently available; confirm separate module pin, electrical and mechanical requirements before carrier design.

Build your edge AI product with Rhino Core IQ9

Share your model, peripheral, mechanical and system requirements to define the product and delivery configuration together.