NVIDIA · Pascal (derived from codename prefix) · 2016
Quadro GP100
Quadro GP100: 16 GB HBM2, 235 W, 3,584 CUDA cores. Launched October 1, 2016.
- Memory
- 16 GB
- Power
- 235 W
- Bus width
- 4,096 bit
Memory16 GB
7 of 183 in Quadro
Power235 W
7 of 161 by higher draw in Quadro
CUDA cores3,584
4 of 129 in Quadro
Current market
Affiliate links — we may earn a commission.
Specifications
Memory
- Capacity
- 16 GB
- Memory type
- HBM2
- Bus width
- 4,096 bit
- Memory clock
- 703 MHz
- Bandwidth
- 720 GB/s
Compute
- CUDA cores
- 3,584
- SM count
- 56
- TMUs
- 224
- ROPs
- 128
- FP32
- 10,336 GFLOPS
- FP64
- 5,168 GFLOPS
- Pixel fill rate
- 184.7 GP/s
- Texture fill rate
- 323 GT/s
Clocks
- Base clock
- 1,304 MHz
- Boost clock
- 1,442 MHz
Board
- TDP
- 235 W
- Bus interface
- PCIe 3.0 x16
- Form factor
- mobile
Physical
- Architecture
- Pascal (derived from codename prefix)
- Codename
- GP100-876-A1
- Process
- 16 nm
- Series
- Quadro
- Launch date
- October 1, 2016
Not recorded by the source: generation, transistors, die size and external power required, or 1 further field.
Die figure
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.
Catalog context
Within its series, the Quadro GP100 ranks 7th of 138 for FP32 throughput and 7th of 183 for memory capacity. Its 235 W TDP is above the 75 W PCIe slot-power ceiling.
Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16