RTX PRO 6000 Blackwell Workstation Edition
A desktop card with 96 GB of memory for local model work and graphics. Its 1.792 TB/s specification differs from the Server Edition’s 1.597 TB/s.
GDDR7 ECC
Published peak, not measured application throughput
Workstation, Max-Q and Server Edition share shortened names. A cloud listing that says RTX PRO 6000 does not establish this edition or its bandwidth.
When this is a sensible choice
Start here if…
Consider it when one workstation must run local inference, visualization and rendering. Keeping a supported model on one card avoids distributing its weights across a slower host fabric.
Choose another configuration if…
Check chassis airflow, power supply and sustained load before treating a workstation board as a rack-server replacement. HBM-based cards remain a separate bandwidth comparison.
Specifications with their boundaries attached
- Architecture
- Blackwell
- Memory
- 96 GB GDDR7 ECC
- Memory bandwidth
- 1.79 TB/s per accelerator
- Peak compute
- 4,000 TOPS FP4 with sparsity (vendor peak); not a dense BF16 figure
- Scale-up interconnect
- PCIe platform; peer-to-peer support and topology require verification
- Host attachment
- PCIe 5.0; desktop workstation card
- Power
- 600 W maximum consumption
- Partitioning
- Verify exact edition and driver; shared product copy also references Max-Q
- Catalogue status
- Documented product
Compute figures are theoretical peaks at the stated precision. Dense and structured-sparse rates must not be mixed. Bandwidth labelled bidirectional combines both directions. See the source documents.
Three bandwidths, three different jobs
PCIe platform; peer-to-peer support and topology require verification
InfiniBand, RoCE, EFA or provider-specific transport
Where it appears in provider documentation
No provider configuration has been verified for this exact variant in this reference. Consult the linked manufacturer documentation; catalogue absence here is not evidence that the hardware is unavailable.
Model fit and software support
These publisher or serving-engine documents mention this hardware family. They have not been reproduced on our machines.
No model-specific recipe in our reviewed set certifies this exact hardware. The memory calculator can narrow candidates, but it cannot establish software support. Read the model register.
What is the memory floor?
Start with total parameters, then add the memory the workload needs. This arithmetic does not certify a serving configuration. All output sizes below are decimal GB.
Override device capacity with the memory exposed by your allocation, particularly for cloud B300 and partitioned devices. The starting 32 GB budget and 15% reserve are editable teaching assumptions. They are not measurements for the selected model. Mixed-precision tensors, quantization scales, vision encoders and draft models can increase the weight payload.
Raw weights only
320B × 8 bits ÷ 8
Budget per device
96 GB × (1 − 15%)
Arithmetic lower bound
round up ((weights + 32) ÷ budget)
This assumes perfectly balanced sharding. A result of three does not prove that a three-device parallel layout is supported. Check layer/expert divisibility, actual allocatable memory, precision kernels and the fabric before renting.
320B is the model card’s total; 18B active is not its storage size. The vLLM recipe reports about 306 GiB for the native FP8 checkpoint. Hopper requires BF16 KV for this model; the documented ROCm path targets gfx950, not every Instinct GPU. Read the model source ↗
For full training, also budget gradients, optimizer states, activations and communication buffers. The inference weight estimate above is insufficient.
Tokens per second, TTFT and TPOT are not certified for this hardware in our reference. Use the benchmark checklist to compare an exact model, software revision and workload.
Nearby memory capacities, different tradeoffs
These are comparison candidates selected by memory capacity, not performance rankings or drop-in replacements.
RTX PRO 6000 Blackwell Server Edition
96 GB of GDDR7 makes this an interesting inference and mixed AI/graphics card. Its memory capacity sits above H100, but its bandwidth does not.
NVIDIA H100 NVL
H100 NVL is a 94 GB PCIe GPU often discussed as a two-card, 188 GB pair. Always count how many cards the listing includes.
NVIDIA A100 80 GB SXM
80 GB of HBM on the SXM4 form factor. A100 remains useful for BF16 training and supported inference, but cannot execute Hopper’s native FP8 Tensor Core path.
Sources and review scope
Manufacturer and cloud documentation checked 2026-09-12. We reviewed specifications and the stated product boundaries; we did not run training or serving benchmarks on this device. Cloud memory and availability can differ by configuration.
- NVIDIA RTX PRO 6000 Blackwell Workstation specifications ↗ · checked 2026-09-12
Cite this reference
AI Infra Interviews. RTX PRO 6000 Blackwell Workstation Edition: specifications and workload fit. Reviewed . https://aiinfrainterviews.com/hardware/rtx-pro-6000-workstation
Include your access date when citing a changing specification. Link to the specification section for hardware figures or the explanation for a sizing or workload decision.
Research method and limits
We compile manufacturer specifications, cloud documentation, model cards and serving recipes. The reference preserves source units and distinguishes individual devices from nodes and racks. Conflicting figures and unknown fields remain labelled.
Our contribution is the comparison, unit reconciliation, worked arithmetic and workload explanation. Published peaks are vendor specifications. Calculator results are estimates under the displayed assumptions. Neither is a measurement from our own accelerator lab.
For a manufacturer’s specification, consult the original source documents. Cite our page when using its analysis, and retain primary-source attribution for underlying figures. This curated reference does not establish market share, live availability or a universal performance ranking.
Found a discrepancy? Send a correction with the page URL, exact variant, disputed figure and supporting primary document.