gpuindex

NVIDIA · Blackwell (derived from codename prefix) · 2025

RTX PRO 6000 Blackwell Max-Q Workstation Edition

Memory96 GB1 of 40 in RTX
Power300 W2 of 38 by higher draw in RTX
CUDA cores24,0641 of 38 in RTX
Launch price$8,5651 of 22 in RTX

Silicon, made visible

Die area is drawn against the largest recorded die in the catalog. Shader dots use a labeled, card-specific ratio so both early and modern GPUs remain legible.

Die size not recorded · 24,064 shadersDie size not recorded; shader grid shown without scale. Each dot = 256 shaders.24,064 shadersEach dot = 256 shadersDie size not recorded; shader grid shown without scale

Specifications

Memory

Capacity
96 GB
Type
GDDR7
Bus width
512 bit
Memory clock
1,750 MHz
Bandwidth
1,792 GB/s

Compute

CUDA cores
24,064
TMUs
752
ROPs
192
FP32
110,100 GFLOPS
FP64
1,721 GFLOPS
Pixel fill rate
439.3 GP/s
Texture fill rate
1,721 GT/s

Clocks

Base clock
1,590 MHz
Boost clock
2,288 MHz

Board

TDP
300 W
Bus interface
PCIe 5.0 x16
Form factor
mobile
Launch MSRP
8,565 USD

Physical

Architecture
Blackwell (derived from codename prefix)
Codename
GB202
Process
4 nm (mapped from a reviewed process name)
Series
RTX
Launch date
March 18, 2025

Not recorded by the source: generation, transistors, die size and sm count, or 1 further field.

Catalog context

Within its series, the RTX PRO 6000 Blackwell Max-Q Workstation Edition ranks second of 45 for FP32 throughput and first of 40 for memory capacity. Its 300 W TDP is above the 75 W PCIe slot-power ceiling.

Every GPU With 16GB+ VRAM · Every GPU With 8GB+ VRAM

Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16