APLUX

High-performance intelligent module

Rhino Core Q85

A compact core for richer AI applications

Integrates QCS8550, LPDDR5X and UFS in a 40 × 40 mm module. Up to 48 TOPS (INT8, dense), multicamera resources and high-resolution video processing provide a compute platform for interactive terminals, edge vision and robotics.

Rhino Core Q85 product view

48 TOPS

Maximum AI performance (INT8, dense)

40 × 40 mm

Module PCB dimensions

12 GB / 16 GB

LPDDR5X configurations

128 GB

UFS storage

A compact core for richer AI applications

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

AI and graphics working together

The Hexagon tensor processor and Adreno 740 work with the CPU to run adapted vision, multimodal and local language models.

Multicamera and ultra-high-definition video

The module exposes five CSI data groups. The platform supports up to 8K60 decoding and 8K30 encoding; software and cooling determine actual task concurrency.

40 mm core with a custom carrier

BTB exposes PCIe, USB / DP and general-purpose buses for carriers tailored to customer form factors, displays and peripherals.

A companion platform for faster integration

Evaluate applications first on X1R, then combine module specifications, hardware references and model tools for product integration.

Explore integration paths for real-world tasks

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

Qualcomm Dragonwing QCS8550

Process vision and multimodal tasks on the device

Vision processingMultimodal interactionLocal models
Up to 48 TOPS(INT8, dense)Platform-rated peak; validate performance for your workload
Illustrative smart camera

Smart Cameras

Combine cameras, ISP and local inference for more complex visual models and multitasking in intelligent vision devices.

Platform fit
Run multitask detection and content understanding with vision processing and local AI compute.
Module integration
Plan camera carriers around five MIPI CSI groups; confirm channel count, synchronization and concurrency for the sensor solution.
Visual inputMultitask inferenceDetection feedback
View interfaces and integration
Illustrative AI assistant terminal

AI assistant

Connect voice, vision and local models to explore conversation, content understanding and task assistance.

Platform fit
Combine voice, vision and local models in interactive devices that understand inputs and respond to tasks.
Module integration
Combine camera, audio and display resources on the carrier to connect microphone arrays and interactive peripherals.
Voice and visionLocal understandingInteractive feedback
View interfaces and integration
Illustrative AI box

AI box

Connect cameras, networks and existing equipment to run recognition, analytics and intelligent applications in a compact compute device.

Platform fit
Deploy more complex models to edge nodes and return analytical results to existing equipment.
Module integration
Use PCIe, USB and external networking to design an AI box; the carrier must implement RJ45, CAN / RS485.
Device connectivityLocal analyticsBusiness integration
View interfaces and integration
Illustrative consumer AI terminal

Consumer AI terminal

Combine content, models and application interfaces with local multimodal capabilities in display-equipped interactive products.

Platform fit
Combine multimodal input and graphics to provide local interaction on smart display devices.
Module integration
Use MIPI DSI / DP and audio resources for display-equipped terminals; define peripherals, power and enclosure separately.
Multimodal inputModel processingDisplay interaction
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 Q85 specifications

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

Compute and storage

Rhino Core Q85 · Compute and storage
Compute platformQualcomm Dragonwing QCS8550
Process4 nm
CPUQualcomm Kryo, six-core (AA) / eight-core (AC), up to 3.2 GHz; according to the order configuration
NPUQualcomm Hexagon
AI performance (INT8, dense)Up to 48 TOPS(INT8, dense)
AI performance (FP16)Up to 12 TOPS(FP16)
GPUQualcomm Adreno 740,680 MHz
Memory12 GB / 16 GB LPDDR5X
Storage128 GB UFS

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

AA six-core, AC eight-core and other variants differ by SKU. Confirm CPU, memory and system image against the order configuration.

Build your edge AI product with Rhino Core Q85

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