Power rating
Published detailSingle PSU: 1,350 W at 115 V or 1,700 W at 200 V and above. Dual supplies support redundancy or up to 2,700 W aggregate output; configuration matters. [1]
Product image
Manufacturer product image. The selected configuration may vary.
Product photo & illustrative 3D · configuration may varySource
Sourced specifications
Expandable towerHP Z8 Fury G6i
Intel Xeon 600 · RTX PRO 6000 Blackwell Max-Q option
An expandable Xeon workstation supporting up to four RTX PRO 6000 Blackwell Max-Q GPUs. Configure it for a workstation or a larger shared inference service.
96 GB per GPU · up to 4 GPUsReference memory
x86-64CUDA ecosystem
Compared withNVIDIA DGX StationHP ZGX FuryLenovo ThinkStation P7
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 dedicated space and a facilities review for heavily populated systems. HP requires two separate circuits when two power supplies are fitted. A lighter configuration may suit an office after verification.
Electrical input
Published detailAvailable PSU output depends on input voltage. HP’s site guide warns that a fully loaded 1,350 W configuration can draw up to 15 A at 110 V. [2]
Outlet & circuit
Published detailA system fitted with two 1,350 W PSUs must use two different circuits. HP calls for office air conditioning to accommodate the additional heat. [2]
Machine cooling
Published detailFan cooling with configurable performance modes. HP requires 15.24 cm (6 in) clearance on each side except the supporting surface for non-rack installations; keep the rack installation’s front, rear and upper gap clear. [2][3]
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
Published detailHP offers Quiet, Performance and Ultimate Performance modes. It warns that fans can still run hard with multiple high-power GPUs, even in Quiet mode. No comparable AI-load dB(A) result verified. [3]
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
- 439.1 × 219.4 × 558.8 mm
- Weight
- From 22.2 kg
- 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.
- Confirm whether the quote uses one supply, redundant supplies or aggregate mode, and size the installation for the actual CPU and GPU population.
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.
THE PLATFORM BEHIND THE MACHINE
RTX PRO 6000
2 catalog configurations
BEYOND THE SPECIFICATION
Lessons for running this machine.
Published guidance and checklists to help you investigate the full deployment.
Engineering applications
Local 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
Offline operationDoes the whole application work offline?
Local model inference is one part of the path. Test retrieval, documents, identity, tools and restart behavior as well.
Evaluation checklist
Shared inferenceOne box. Several applications. Where is the limit?
Move beyond a single chat window: measure shared capacity under realistic application traffic.
Evaluation checklist
THE CONFIGURATION
Inside the machine
- Configuration
- 1 × 96 GB RTX PRO 6000 Max-Q screening reference · other components configurable
- CPU / accelerator
- Intel Xeon 600 · RTX PRO 6000 Blackwell Max-Q option
- Memory
- 96 GB per GPU · up to 4 GPUs
- Memory bandwidth
- Confirm selected configuration
- Architecture
- x86-64
- Operating system
- Windows 11 Pro · confirm Linux option
- Storage
- Up to 104 TB · configured drives
ON YOUR PREMISES
Space, power & connectivity
- Form factor
- Expandable tower
- Dimensions
- 439.1 × 219.4 × 558.8 mm
- Weight
- From 22.2 kg
- Power rating
- Single PSU: 1,350 W at 115 V or 1,700 W at 200 V and above. Dual supplies support redundancy or up to 2,700 W aggregate output; configuration matters.
- Connectivity
- Confirm selected configuration
- Availability
- Check regional availability
BEFORE YOU CHOOSE
Up to 2 TB DDR5 ECC system RAM is separate from GPU memory. The memory screen uses one 96 GB GPU.
Multiple GPUs do not automatically form one memory pool. Framework support, sharding and interconnect overhead must be evaluated.
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.
OperationsUnderstand Tech
Offline is a property of the whole stack
Examine what still connects beyond the premises.
For your deployment
Distinguish initial installation, inference, application use, authentication and updates.
Deployment experienceUnderstand Tech
An execution agent beside the test equipment
Confidential Wi-Fi module test automation.
For your deployment
Exact hardware and proprietary test assets are not disclosed. This is an application field record.
THE LOCAL AI WATCH
All updates Updates for this machine
Loading updates…
MEMBER RATINGS · SELF-DECLARED, NOT MEASURED
How members rate the Z8 Fury G6i.
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 Z8 Fury G6i?
Questions, ideas and experience from putting AI machines to work. You do not need a finished deployment to contribute.
Loading the discussion…