Blackwell architecture
NVIDIA RTX Pro 6000
NVIDIA RTX Pro 6000 Blackwell is the current professional flagship: 96 GB of GDDR7 memory, 24,064 Blackwell CUDA cores and fifth-generation Tensor cores — for AI, graphics and accelerated computing in one platform.
- GPU memory
- 96 GB GDDR7 ECC
- Memory bandwidth
- 1,792 GB/s
- CUDA cores
- 24,064
Specifications as published by NVIDIA; Tensor Core ratings shown are sparsity-accelerated figures.
Overview
Why RTX Pro 6000 fits
Blackwell generation, 96 GB GDDR7
RTX Pro 6000 Blackwell doubles the memory capacity and bandwidth of the previous professional generation. With 96 GB of GDDR7, it can hold models, scenes and datasets that previously demanded multi-GPU setups, while fifth-generation Tensor cores bring current-generation AI throughput to professional platforms.
Three editions cover different homes: Workstation, Max-Q Workstation (300 W) and Server Edition for rack deployment. It is the aspirational default for teams wanting one platform for graphics-heavy work and serious local AI. Edition, form factor and configuration are confirmed per engagement.
Specifications
RTX Pro 6000 technical specifications
Published figures for the accelerator, followed by the variant and configuration caveats that apply.
- Architecture
- NVIDIA Blackwell
- GPU memory
- 96 GB GDDR7 with ECC
- Memory interface
- 512-bit
- Memory bandwidth
- 1,792 GB/s
- CUDA cores
- 24,064
- Tensor cores
- 752 (fifth-generation)
- RT cores
- 188 (fourth-generation)
- Bus
- PCIe Gen5
- Editions
- Workstation · Max-Q Workstation · Server Edition
- Power
- Up to 600 W (Max-Q edition: 300 W)
Variant & configuration note
All three editions share the 96 GB GDDR7 buffer; power envelope, cooling and form factor differ (Workstation and Server up to 600 W, Max-Q 300 W). Edition and host configuration are confirmed per engagement. Core counts above follow NVIDIA partner-published figures for the series.
Specifications describe the GPU itself as published by NVIDIA — not a fixed server configuration. Scalenta scopes complete instances (GPU count, interconnect, CPU, memory, storage) per engagement and states them in writing.
Use cases
Where RTX Pro 6000 fits
Workload shapes this platform suits — the scoping conversation maps them to a concrete configuration.
Large-model AI at the desk or in the rack
Fine-tuning, inference and RAG pipelines with 96 GB of memory that holds far larger models on a single GPU.
High-end visual computing
Complex scenes, real-time ray tracing and simulation with fourth-generation RT cores and hardened AI features.
Accelerated engineering and science
CAE, digital twins and data science workloads that blend graphics, AI and floating-point compute.
Delivery model
Partner-sourced, scoped in writing
How GPU capacity is delivered at Scalenta — the same three commitments on every model page.
Partner-sourced capacity
Accelerator capacity is sourced through verified data center and hardware partners — no facility-ownership claims, no stock promises.
Scoped per engagement
Model, variant, GPU count, interconnect and host configuration are confirmed in writing before anything is committed.
Operated with 24/7 support
Deployments are covered by 24/7 support and SLA-backed managed services scoped to your environment.
Related GPU models
Nearby options in the catalogue
NVIDIA RTX 6000 Ada
The current-generation professional graphics flagship: Ada throughput, 48 GB ECC memory, and strong AI capability in one card.
- GPU memory
- 48 GB GDDR6 ECC
- Memory bandwidth
- 960 GB/s
- CUDA cores
- 18,176
NVIDIA L40S
One card for generative AI, 3D graphics, rendering and video — the pragmatic choice where workloads refuse to stay in one lane.
- GPU memory
- 48 GB GDDR6 ECC
- Memory bandwidth
- 864 GB/s
- FP8 tensor
- 1,466 TFLOPS
NVIDIA H100
The proven Hopper accelerator for LLM training and inference, with FP8 Transformer Engine support and 900 GB/s NVLink scale-up.
- GPU memory
- 80 GB HBM3
- Memory bandwidth
- 3.35 TB/s
- FP8 tensor
- 3,958 TFLOPS
FAQ
RTX Pro 6000 — common questions
Which edition should I choose?
Can it replace a data center GPU for training?
How does it fit Scalenta's managed services?
Request a GPU consultation
Talk to us about NVIDIA RTX Pro 6000 — workload-first scoping, written findings and a proposal with clear scope. No obligation.