NVIDIA · Blackwell (derived from codename prefix) · 2025
RTX PRO 6000 Blackwell Max-Q Workstation Edition
Memory96 GB
1 of 40 in RTX
Power300 W
2 of 38 by higher draw in RTX
CUDA cores24,064
1 of 38 in RTX
Launch price$8,565
1 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.
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.
Explore related indexes
Every GPU With 16GB+ VRAM · Every GPU With 8GB+ VRAM
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16