GPUSPECINDEX

NVIDIA · Tesla · 2007

C870 GPU Computing Module

C870 GPU Computing Module: 1,536 MB GDDR3, 170.9 W, 128 CUDA cores. Launched May 2, 2007.

Memory
1,536 MB
Power
170.9 W
Bus width
384 bit
Memory1,536 MB32 of 32 in Data Center
Power170.9 W35 of 40 by higher draw in Data Center
CUDA cores12846 of 47 in Data Center

Affiliate links — we may earn a commission.

Memory

Capacity
1,536 MB
Memory type
GDDR3
Bus width
384 bit
Bandwidth
76.8 GB/s

Compute

CUDA cores
128
SM count
16
TMUs
32
ROPs
24
FP32
345.6 GFLOPS

Clocks

Base clock
1,350 MHz

Board

TDP
170.9 W
Form factor
datacenter

Physical

Architecture
Tesla
Series
Data Center
Launch date
May 2, 2007

Not recorded by the source: generation, codename, process and transistors, or 9 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 · 128 shadersDie size not recorded; shader grid shown without scale. Each dot = 1 shader.128 shadersEach dot = 1 shaderDie size not recorded; shader grid shown without scale

Within its series, the C870 GPU Computing Module ranks 36th of 36 for FP32 throughput and 32nd of 32 for memory capacity. Its 170.9 W TDP is above the 75 W PCIe slot-power ceiling.

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