Power rating
Not verifiedNo complete-system power rating verified in the reviewed sources.
Manufacturer product image. The selected configuration may vary.
Qualcomm Dragonwing IQ8 · STM32H5
An edge AI computer that brings local models, computer vision and real-time control onto one board.
BEFORE IT ARRIVES
What this configuration needs on your premises.
A development board for a lab bench or integrated product. Budget power and cooling for the board, enclosure and attached devices together.
No complete-system power rating verified in the reviewed sources.
Store specifications list USB-C at 5 V / 3 A maximum, a 12–24 V DC barrel input and a 7–24 V DC screw terminal. Arduino’s tutorial instead refers to a 65 W USB-C supply and 7–24 V barrel input; confirm the board revision and power path before choosing a supply. [1][2]
No machine-specific branch-circuit requirement verified. Check the nameplate, regional cord and other loads on the same circuit.
The exact cooling assembly is not documented in the reviewed source. Request the thermal and installation specification.
Commercial operating range listed as −10–60°C. That board rating does not establish thermal limits for a finished enclosure or attached peripherals. [1]
No comparable noise measurement under an AI workload verified. Ask for dB(A), distance, workload and ambient conditions; audition it before placing it beside people.
ACTUAL CONSUMPTION
PSU capacity, chip TDP and measured consumption describe different things. Only measurements with a stated configuration and test method appear here.
No attributable wall-power test for this configuration was established in this review. Measure at the outlet with the exact model, workload, runtime and power mode recorded.
Plan for the computer and its power supply to heat the room. Check ventilation during long jobs and when several machines share a small office.
Lab planning guidance. Office suitability depends on the installed configuration, shared circuits, heat removal and acceptable noise; a workstation label alone does not settle it.
Enter average power at the wall for the hours you are modeling, or an explicit planning assumption. Supply wattage and chip TDP are not consumption measurements.
Add wall power to calculate a scenario.
Scenario only. Hours outside this period are excluded: include idle time for an always-on system. Displays, networking, UPS losses and room air conditioning are extra. Heat assumes the computer and power supply release their heat into this room; it does not size a circuit or an HVAC system. Currency selects your tariff’s unit, with no conversion.
Manufacturer documentation and attributed first-hand hardware inspections, scoped to the named model or configuration. “Not verified” identifies a gap in this review, not a claim that the manufacturer has no documentation. Installation assessments are the Lab’s interpretation.
Keep sensitive processing on your infrastructure. Inspect every connection in the complete stack.
Control access, connectivity and updates. A local machine still needs a secure deployment.
Generate tokens on your own compute. Understand the full cost of the useful work it delivers.
SHARED WORK AROUND THIS PLATFORM
Reference-platform guidance and field records. Exact OEM configurations need their own validation.
Share the software, configuration and evidence from your own system.
Contribute a setupTHE PLATFORM BEHIND THE MACHINE
1 catalog configuration
BEYOND THE SPECIFICATION
Published guidance and checklists to help you investigate the full deployment.
An execution agent and confidential engineering test assets show how on-premises AI extends beyond office applications.
Local model inference is one part of the path. Test retrieval, documents, identity, tools and restart behavior as well.
Put quality, retries, utilization and operating effort beside token throughput.
THE CONFIGURATION
ON YOUR PREMISES
BEFORE YOU CHOOSE
Manufacturer specifies 40 dense TOPS and 16 GB shared LPDDR5 memory. TOPS is not an LLM tokens-per-second benchmark.
A physical-AI evaluation needs the actual sensor, camera or actuator setup as well as the compute board.
The Lab’s generic LLM memory heuristic is conservative and is not a prediction of NPU model support.
Manufacturer specificationsHelp improve this record. Suggest a correction
IN THE FIELD
Operating records from customers, contributors and the Lab.
In an office, a factory, an engineering lab or beside your test equipment. Share a deployment and keep the people behind it credited.
Contribute a deploymentTHE SHARED TECHNICAL LIBRARY
Supplier recipes, community experience and UT’s deployment lessons, connected to the hardware.
Examine what still connects beyond the premises.
Distinguish initial installation, inference, application use, authentication and updates.
Confidential Wi-Fi module test automation.
Exact hardware and proprietary test assets are not disclosed. This is an application field record.
Loading updates…
MEMBER RATINGS · SELF-DECLARED, NOT MEASURED
One rating per member, tied to a Lab profile. Stars count immediately; written verdicts are published after a quick review by the Lab team. A rating is an opinion about fit for a job, not a benchmark.
THE PEOPLE BEHIND THE MACHINES
Questions, ideas and experience from putting AI machines to work. You do not need a finished deployment to contribute.
Loading the discussion…
THE MACHINE × THE MODEL × THE WORKLOAD
Connect the model, serving stack, workload and cost of operating this box.
Arduino documents local language, vision and audio workloads for VENTUNO Q. The Lab has not yet indexed a complete checkpoint, quantization and runtime manifest for this board.
Explore Arduino’s model and platform guidance
Contribute your configurationEach measured result belongs to one box configuration, one model, one serving stack and one workload. Publish latency, per-stream speed, request rate, errors and task quality together.