96 GB on one GPU
Keep memory-intensive scenes and model workloads on a single card where they fit. ECC memory supports error detection and correction; usable capacity still depends on the software and workload.
PERCEPTA / PROFESSIONAL GRAPHICS
NVIDIA RTX PRO 6000 Blackwell
Workstation Edition 96GB
96 GB of ECC graphics memory. NVIDIA Blackwell architecture. Purpose-built for professional workloads.
Product preview
Discuss this GPU
Explore the specification
Pricing and availability to be confirmed. Not currently available to order or pre-order.
Manufacturer reference imagery. GPU card only; not a complete system.
Workstation Edition
A workstation GPU for demanding local workloads.
For a dedicated workstation handling large 3D scenes, GPU rendering, visualisation or local AI development. This is the full-power Workstation Edition: 96 GB of ECC GDDR7 memory with active double-flow-through cooling and a 600 W board-power specification. Chassis clearance, power delivery and airflow need to be planned around the card.
96 GBGDDR7 memory with ECC
1,792 GB/sPublished memory bandwidth
600 WTotal board power
PCIe 5.0x16 host interface
Rendering and display
Fourth-generation RT cores support ray-traced workloads, while four DisplayPort outputs provide direct monitor connections. Application, driver and display configuration determine the features available.
Full-power workstation design
A dual-slot card with an extended-height cooler. Its 600 W power envelope and double-flow-through airflow distinguish it from the smaller 300 W Max-Q edition.
Technical specification
Manufacturer reference / checked 11 Sep 2026| Edition | Workstation Edition |
|---|---|
| GPU architecture | NVIDIA Blackwell / GB202 |
| CUDA compute capability | 12.0 |
| CUDA cores | 24,064 |
| Tensor cores | 752 / fifth generation |
| RT cores | 188 / fourth generation |
| Graphics memory | 96 GB GDDR7 with ECC |
| Memory interface | 512-bit |
| Memory bandwidth | 1,792 GB/s |
| Host interface | PCIe 5.0 x16 |
| Total board power | 600 W |
|---|---|
| Cooling | Active double-flow-through |
| Form factor | Extended-height, dual-slot |
| Nominal dimensions (height x length) | 5.4 x 12 inches; additional installation clearance required |
| Auxiliary power | 1 x PCIe CEM5 16-pin |
| Display connectors | 4 x DisplayPort 2.1b |
| Display operation | Direct display output; enabling MIG compute mode disables physical display outputs |
| NVLink bridge | Not supported |
| Frame synchronisation | Supports separate NVIDIA RTX PRO Sync hardware; not included by this listing |
| FP32 compute | 126 TFLOPS |
|---|---|
| RT core throughput | 382 TFLOPS |
| AI compute (FP4, with sparsity) | 4,000 AI TOPS |
These are manufacturer-published peak figures, not measured application benchmarks or guarantees. Throughput varies with software, workload, power configuration and operating conditions. Different precision and RT metrics are not interchangeable. AI TOPS uses effective FP4 with sparsity; the NVIDIA datasheet specifies GPU Boost-clock peaks. Values follow the June 2026 NVIDIA Workstation datasheet (126 FP32 / 382 RT TFLOPS); some web summaries retain earlier 125 / 380 figures.
| Video encoding | 4 x ninth-generation NVENC engines |
|---|---|
| Video decoding | 4 x sixth-generation NVDEC engines |
| JPEG engines | 4 |
| Video processing | AV1 support; 4:2:2 encode/decode support with compatible software |
| Multi-Instance GPU (MIG) | Up to 4 instances; supported profiles include 4 x 24 GB, 2 x 48 GB or 1 x 96 GB |
| NVIDIA vGPU technology | Not supported on this edition |
Nominal card dimensions are not shipping dimensions or a guaranteed maximum installation envelope. MIG profile, driver and system requirements apply; memory partitioning is not automatic multi-GPU memory pooling.
Will it fit my workstation or server?
For an existing workstation, provide the case, motherboard and PSU model, other installed expansion cards, and your software workload. The 600 W figure is GPU board power, not a recommended whole-system PSU rating. Cable routing and ventilation must follow the selected board and system guidance.
Which RTX PRO 6000 edition should I choose?
Choose Workstation Edition when your validated workstation can accommodate its extended-height 600 W active cooler and you want the higher published peak throughput of the workstation pair. Choose Max-Q when a 300 W blower-cooled design is more appropriate. Neither workstation edition supports NVIDIA vGPU technology.
What should I know about MIG and software licences?
MIG supports hardware partitioning on this edition, but NVIDIA vGPU technology is not supported. Current NVIDIA instructions require a supported software stack and compute mode for MIG; compute mode disables the card's physical display outputs. Do not assume MIG automatically creates independently assignable virtual GPUs across multiple VMs.
What is included, and can I pre-order?
This is a product preview for one GPU card, not a complete computer. We are not taking orders or pre-orders for this item yet. Price, exact supplied board and part number, condition, accessories, warranty terms and delivery timing will be confirmed before it is offered for sale.
Manufacturer imagery illustrates the edition, not stock currently held by Percepta. No software subscription, Sync board, power adapter or other accessory is promised by this listing.
Manufacturer documentation and specification notes
Hardware details are checked against the references below. Specifications describe the named edition; supplier-specific commercial details remain subject to confirmation. Reference images are credited to NVIDIA/PNY.
Planning a workstation or server build? Send us your system details and intended workload so we can discuss the appropriate edition.
Discuss your requirement ↗