MPN: RTXPRO6000MQ·By: NVIDIA
Ships from the US.
The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, SKU RTXPRO6000MQ, is a workstation GPU designed around the NVIDIA Blackwell architecture for professional environments. It integrates 96 GB of GDDR7 memory with ECC on a 512 bit interface and delivers up to 1792 GB per second of memory bandwidth. The card connects via PCI Express 5.0 x16 and features a blower active fan thermal solution in a full height, full length, dual slot form factor measuring 5.4 inches high and 12 inches long. Power consumption is specified at up to 300 W, supported by a single PCIe CEM5 16 pin power connector. The board provides four DisplayPort 2.1 display connectors for multi display setups. Additional capabilities include Multi Instance GPU support with configurations up to 4x 24 GB, 2x 48 GB, or 1x 96 GB to optimize GPU sharing across workloads.
| Manufacturer part # | RTXPRO6000MQ |
|---|---|
| Brand | NVIDIA |
| Condition | New |
| Model | RTX PRO 6000 Blackwell Max-Q Workstation Edition |
| RT Cores | 188 (4th Generation) |
| CUDA Cores | 24,064 |
| GPU Memory | 96 GB GDDR7 |
| ECC Support | Yes |
| Form Factor | Dual slot, full height, full length |
| MIG Support | Up to 4 MIGs at 24 GB each |
| Compute APIs | CUDA 12.8, OpenCL 3.0, DirectCompute |
| Product Line | NVIDIA RTX PRO |
| Product Type | Workstation graphics card |
| Tensor Cores | 752 (5th Generation) |
| Graphics APIs | DirectX 12, Shader Model 6.6, OpenGL 4.63, Vulkan 1.3 |
| NVLink Support | No |
| Cooling Solution | Active cooling |
| GPU Architecture | NVIDIA Blackwell architecture |
| Display Connectors | 4 x DisplayPort 2.1b (disabled by default) |
| FP4 AI Performance | 3.511 PFLOPS peak (with sparsity) |
| RT Core Performance | 333 TFLOPS peak |
| Encode Decode Engines | 4 x NVENC encode, 4 x NVDEC decode, 4 x JPEG |
| vGPU Software Support | No support |
| Maximum Simultaneous Displays | Up to 4 displays |
| FP32 Single Precision Performance | 110 TFLOPS peak |
| Maximum Display Resolution 2x7680x4320 | 2 x 7680 x 4320 at 60 Hz |
| Maximum Display Resolution 4x4096x2160 | 4 x 4096 x 2160 at 120 Hz |
| Maximum Display Resolution 4x5120x2880 | 4 x 5120 x 2880 at 60 Hz |
| Memory Bandwidth | Up to 1792 GB/s |
|---|
| Maximum Power Consumption | 300 W |
|---|
| Host Interface | PCIe 5.0 x16 |
|---|---|
| Memory Interface | 512-bit |
Environments that benefit from Multi Instance GPU, using up to 4x 24 GB, 2x 48 GB, or a single 96 GB instance to partition GPU resources for multiple isolated workloads.
Workloads that leverage 96 GB of GDDR7 memory with ECC and up to 1792 GB per second of memory bandwidth on a 512 bit interface for large datasets.
Systems requiring a PCI Express 5.0 x16 workstation GPU with a 300 W power envelope and a dual slot, full height, full length form factor.
Setups that use four DisplayPort 2.1 connectors to drive multiple high resolution displays from a single workstation GPU.
Shared lab or team environments partitioning the GPU via Multi Instance GPU modes up to 4x 24 GB or 2x 48 GB, aligning resources with different users or jobs.
The RTX PRO 6000 Blackwell Max-Q Workstation Edition is equipped with 96 GB of GDDR7 memory with ECC on a 512 bit memory interface. It delivers up to 1792 GB per second of memory bandwidth. This configuration supports data intensive workloads and benefits from error correcting code for improved reliability in professional environments.
The RTXPRO6000MQ uses a PCI Express 5.0 x16 graphics bus. This means it is designed for systems that provide a full height, full length PCIe 5.0 x16 slot. Aligning the GPU with PCIe 5.0 capable platforms helps ensure high throughput between the GPU and the host CPU and memory.
The GPU has a maximum power consumption of 300 W and uses a blower active fan thermal solution. It occupies a dual slot, full height, full length form factor measuring 5.4 inches high and 12 inches long, and it is powered via a single PCIe CEM5 16 pin connector. These parameters help determine chassis, power supply, and cooling design.
The card provides four DisplayPort 2.1 display connectors. These four ports allow it to drive multiple displays from a single GPU, depending on the display specifications and system configuration. For planning multi display workstations, these four DisplayPort 2.1 outputs are the primary consideration from the GPU side.
Yes, the RTX PRO 6000 Blackwell Max-Q supports Multi Instance GPU configurations. It can be partitioned into up to 4 instances of 24 GB, up to 2 instances of 48 GB, or a single 96 GB instance. This allows organizations to allocate GPU resources more granularly across users or workloads on the same physical card.
Details
Shipping, warranty & returns
No reviews yet — be the first to review this part.
Secure SSL checkout. Visa, Mastercard, Amex and Discover accepted. ACH / wire available for businesses.
New, certified-refreshed and OEM stock with guaranteed compatibility, backed by warranty on every part.
We process quotes, POs, stock documentation and compliance invoicing.
[email protected]We'll confirm availability and pricing for RTXPRO6000MQ, usually within one business day.
You might also want to check out these products.
900-22081-0040-000 - NVIDIA Tesla K40 Video Graphic Card