Name: NVIDIA RTX PRO 6000 96GB Blackwell Max-Q Workstation Edition (BULK)
Brand: NVIDIA
SKU: NVrpb02
Availability: Discontinued
Rating: 0 (0 reviews)

All from NVIDIA

Add to the list

NVIDIA RTX PRO 6000 96GB Blackwell Max-Q Workstation Edition (BULK)

NVIDIA RTX PRO 6000 96GB Blackwell Max-Q Workstation Edition (BULK) graphics card

The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition is the first professional workstation GPU built on the NVIDIA Blackwell architecture, delivering 96GB of ultra-fast GDDR7 memory with 1792GB/s of throughput, 24064 CUDA cores, 5th-generation Tensor cores with FP4 support, and 3511 TOPS of AI performance—all in a dual-slot, full-height design with a 300W TBP optimised for configurations with up to four GPUs in a single system. For researchers, AI developers, VFX professionals, and data scientists who need to invest in an infrastructure that is ready for the next decade, the RTX PRO 6000 Blackwell Max-Q is the only answer.

Key features of the NVIDIA RTX PRO 6000 96GB Blackwell Max-Q Workstation Edition (BULK) graphics card

Features 96GB of GDDR7 ECC memory with 1792GB/s throughput on a 512-bit bus—nearly double the capacity and bandwidth of the previous Ada Lovelace generation for training the largest AI models, 8K VFX scenes, and extensive scientific simulations
NVIDIA Blackwell architecture with 24064 CUDA cores and a boost frequency of up to 2288MHz achieves 110 TFLOPS in FP32 and 333 TFLOPS of RT core performance, while new neural shaders integrate neural networks directly into programmable shaders
5th-generation Tensor cores with FP4 precision and DLSS 4 Multi Frame Generation achieve 3511 TOPS of performance—up to 3× the performance of the previous generation—enabling local LLM fine-tuning, AI model prototyping, and generative AI workflows directly on the workstation
4th-generation RT cores with 333 TFLOPS of performance deliver double the ray-triangle intersection speed of the previous generation, and RTX Mega Geometry technology processes up to 100× more ray-traced triangles for physically accurate scenes with billions of polygons
Multi-Instance GPU (MIG) allows the card to be divided into up to four fully isolated instances—configurable as 4× 24GB, 2× 48GB, or 1× 96GB—each with its own memory, cache, and compute cores for secure concurrent work by multiple users or workloads
Four 9th-generation NVENC video encoders and four 6th-generation NVDEC decoders with support for 4:2:2 10-bit H.264 and HEVC encoding enable real-time professional video processing for multi-cam productions, live broadcasting, and VFX workflows
Max-Q design with a 300W TBP and 1× PCIe CEM5 16-pin power connector is optimised for deploying up to four GPUs in a single system, scaling total performance to 12000 TOPS of AI and 384GB of shared GDDR7 memory
Four DisplayPort 2.1b outputs enable multi-display operation at resolutions up to 8K at 240Hz or 16K at 60Hz with HDR and extended colour depth for precise graphics and visualisation workflows
The card is supplied in BULK packaging without a retail box or accessories, making it ideal for system integrators and OEM builds—while its performance and specifications are identical to the retail version

Memory that defines a new class of performance

GDDR7 memory is not just an evolution of GDDR6—it's a fundamental change in how a GPU processes data. The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition combines 96GB of GDDR7 ECC with a throughput of 1792GB/s on a 512-bit bus, which corresponds to nearly double the capacity and throughput of the previous flagship professional card of the Ada Lovelace generation. In practice, this means that models and scenes that previously required a multi-GPU configuration or cloud infrastructure now run comfortably on a single card—and a four-card RTX PRO 6000 Blackwell Max-Q configuration offers a total of 384GB of shared memory for the most ambitious projects.

A new benchmark for local AI infrastructure

Performance of 3511 TOPS combined with FP4 precision support in the 5th-generation Tensor cores moves the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition into a category that was previously exclusive to data centres. The card handles LLM fine-tuning, generative AI, domain-specific model training, and inference of natively large networks locally, with full control over data and without recurring cloud costs. DLSS 4 Multi Frame Generation then adds up to a 3× higher frame rate in supported rendering applications and simulations, while the AI Management Processor ensures intelligent distribution of computing resources across workloads.

RTX Mega Geometry and neural shaders

Until now, ray tracing has been limited by the number of polygons a GPU could process in real time. 4th-generation RT cores with RTX Mega Geometry technology raise this limit by an order of magnitude: the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition handles up to 100× more ray-traced triangles than the previous generation, paving the way for physically accurate scenes with billions of polygons without offline rendering. New neural shaders integrate neural networks directly into programmable shaders, so AI is no longer a post-processing layer but becomes a natural part of the graphics pipeline. For architects, VFX artists, product designers, and researchers, this means visualisations that faithfully reflect physical reality—in real time.