GPUSPECINDEX

NVIDIA · Volta · 2018

V100 GPU accelerator (PCIe FHHL card)

V100 GPU accelerator (PCIe FHHL card): 16 GB HBM2, 250 W, 5,120 CUDA cores. Launched March 27, 2018.

Memory
16 GB
Power
250 W
Bus width
4,096 bit
Memory16 GB13 of 32 in Data Center
Power250 W17 of 40 by higher draw in Data Center
CUDA cores5,12013 of 47 in Data Center

Affiliate links — we may earn a commission.

Memory

Capacity
16 GB
Memory type
HBM2
Bus width
4,096 bit
Bandwidth
829.4 GB/s

Compute

CUDA cores
5,120
SM count
80
TMUs
320
ROPs
128
FP32
13,210 GFLOPS
FP64
6,605 GFLOPS

Clocks

Base clock
937 MHz
Boost clock
1,290 MHz

Board

TDP
250 W
Form factor
datacenter

Physical

Architecture
Volta
Series
Data Center
Launch date
March 27, 2018

Not recorded by the source: generation, codename, process and transistors, or 7 further fields.

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 · 5,120 shadersDie size not recorded; shader grid shown without scale. Each dot = 64 shaders.5,120 shadersEach dot = 64 shadersDie size not recorded; shader grid shown without scale

Within its series, the V100 GPU accelerator (PCIe FHHL card) ranks 14th of 36 for FP32 throughput and 13th of 32 for memory capacity. Its 250 W TDP is above the 75 W PCIe slot-power ceiling.

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