Power rating
Published detail1,600 W Titanium PSU capacity at 115–240 V; lower 12 V rail capacity at 100–114 V. [1]
Product image
Manufacturer product image. The selected configuration may vary.
Product photo & illustrative 3D · configuration may varySource
Sourced specifications
Tower / 5U rackSupermicro Super AI Station · ARS-511GD
GB300 Grace Blackwell Ultra
A GB300 system that moves from tower to 5U rack with an optional kit, bridging deskside experiments and an on-premises installation.
496 GB CPU + 252 GB GPUReference memory
arm64CUDA ecosystem
Compared withNVIDIA DGX Station
BEFORE IT ARRIVES
Power, cooling & your space.
What this configuration needs on your premises.
Lab assessment · based on the evidence below
Plan an equipment space
Plan a ventilated equipment space for sustained shared workloads. A suitable office is possible after checking power, noise and physical access; its internal liquid loop does not require a data center by itself.
Electrical input
Published detail1,600 W PSU input rating: 115–240 V AC, 50–60 Hz. Confirm the delivered cord and low-voltage operating restrictions. [1]
Outlet & circuit
Published detailNVIDIA specifies a 20 A circuit for the DGX Station platform. Have the supplier confirm the exact OEM system, input voltage and regional connection requirements. [3]
Machine cooling
Published detailClosed-loop, direct-to-chip liquid cooling plus chassis fans (two 120 mm, one 80 mm, one 60 mm and one 40 mm). [1][2]
Operating limits
Not verifiedWhole-system ambient temperature and humidity limits are not verified. A power-supply temperature limit is not a system limit.
Noise in the workspace
Not verifiedNo 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
Power at the wall
PSU capacity, chip TDP and measured consumption describe different things. Only measurements with a stated configuration and test method appear here.
Idle and AI-load wall power: not verified.
Share a power measurement 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.
Room cooling
Allow for sustained room heat, including after office hours. A ventilated equipment room may be more practical for multiple systems or continuous jobs. An internal liquid cooler does not remove the need for room cooling.
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.
Space & installation
- Enclosure
- 454.7 × 218.4 × 701 mm · enclosure
- Weight
- 40 kg net
- Keep air inlets and exhausts unobstructed, with room for cables and servicing. An enclosed cupboard needs its own ventilation; the enclosure dimensions are not an airflow clearance.
- Tower or 5U installation. Confirm rack rails, cabinet depth, loaded weight and servicing access; rack mounting is an option, not a data-center requirement.
Estimate electricity use & room heat
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.
Sources & review scope (3)
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.
Opening model configurations…
01 / PRIVACY
Your data has a home.
Keep sensitive processing on your infrastructure. Inspect every connection in the complete stack.
02 / SECURITY
You set the boundaries.
Control access, connectivity and updates. A local machine still needs a secure deployment.
03 / TOKEN ECONOMICS
Own the capacity.
Generate tokens on your own compute. Understand the full cost of the useful work it delivers.
SHARED WORK AROUND THIS PLATFORM
Setups you can build on.
Reference-platform guidance and field records. Exact OEM configurations need their own validation.
Understand TechField recordLocal AI inside an accounting and advisory firm
A professional-services firm’s on-premises deployment: applications, confidentiality and the expertise to operate the system. The firm is not named at its request.
NVIDIA · indexed by the LabRecipeAn inference endpoint for your local applications
Connect applications to a model server on a GB10 or GB300 reference platform using vLLM.
NVIDIA · indexed by the LabRecipeStructured responses from a local Station
Explore SGLang serving, structured output and the conditions to check on a GB300 workstation.
THE PLATFORM BEHIND THE MACHINE
GB300 / DGX Station
8 catalog configurations
BEYOND THE SPECIFICATION
Lessons for running this machine.
Published guidance and checklists to help you investigate the full deployment.
Infrastructure
Ollama, vLLM, NIM: nine months of deployment learning.
UT’s reported journey across serving stacks, hardware integration and customer feedback. A starting record for the decisions and evidence still to publish.
UT field note
Startup & recoveryA NIM container that took about 30 minutes to start.
An operator-reported startup observation from UT’s GB10/GB300 work. The next step is to identify the exact configuration and separate the startup phases.
UT field note
Engineering applicationsLocal AI beside a Wi-Fi module test bench.
An execution agent and confidential engineering test assets show how on-premises AI extends beyond office applications.
UT field note
THE CONFIGURATION
Inside the machine
- Configuration
- ARS-511GD-NB-LCC · integrated configuration on request
- CPU / accelerator
- GB300 Grace Blackwell Ultra
- Memory
- 496 GB CPU + 252 GB GPU
- Memory bandwidth
- GPU 7.1 TB/s · CPU 396 GB/s
- Architecture
- arm64
- Operating system
- Ubuntu with NVIDIA AI Developer Tools
- Storage
- 4 M.2 slots · configured drives
ON YOUR PREMISES
Space, power & connectivity
- Form factor
- Tower / 5U rack
- Dimensions
- 454.7 × 218.4 × 701 mm · enclosure
- Weight
- 40 kg net
- Power rating
- 1,600 W Titanium PSU capacity at 115–240 V; lower 12 V rail capacity at 100–114 V.
- Connectivity
- 2 × 400 GbE · 10 GbE · IPMI / Redfish
- Availability
- Check regional availability
BEFORE YOU CHOOSE
Optional rackmount kit; confirm rails, rack depth, circuit and acoustic suitability with the integrator.
748 GB combines 252 GB GPU and 496 GB CPU memory. An optional display GPU has its own separate memory.
Manufacturer specificationsHelp improve this record. Suggest a correction
IN THE FIELD
Deployment experiences
Operating records from customers, contributors and the Lab.
Where does your AI run?
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
Knowledge around this machine.
Supplier recipes, community experience and UT’s deployment lessons, connected to the hardware.
RecipesSupplier
NVIDIA’s workstation playbooks
Browse serving, development and application guides.
For your deployment
Individual playbooks have their own hardware support matrices. Do not assume all target both platforms.
OperationsUnderstand Tech
Our journey from Ollama to vLLM to NIM
Why runtime selection became an operating decision at UT.
For your deployment
The narrative is operator-reported. Pinned versions and comparable results are still to be attached.
TroubleshootingUnderstand Tech
Investigating a 30-minute startup
Separate download, preparation, model loading and service readiness.
For your deployment
An open investigation, not a diagnosed universal NIM issue. Cold and warm starts need separate measurement.
THE LOCAL AI WATCH
All updates Updates for this machine
Loading updates…
MEMBER RATINGS · SELF-DECLARED, NOT MEASURED
How members rate the Super AI Station · ARS-511GD.
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
Experience with Super AI Station · ARS-511GD?
Questions, ideas and experience from putting AI machines to work. You do not need a finished deployment to contribute.
Loading the discussion…