GPUSPECINDEX

NVIDIA · Fermi (derived from codename prefix) · 2012

GeForce GT 640 OEM Rebrand

GeForce GT 640 OEM Rebrand: 1,536 MB DDR3, 75 W, 144 CUDA cores. Launched April 24, 2012.

Memory
1,536 MB
Power
75 W
Bus width
192 bit
Memory1,536 MB29 of 94 in GeForce GT
Power75 W4 of 91 by higher draw in GeForce GT
CUDA cores14433 of 104 in GeForce GT

Affiliate links — we may earn a commission.

Memory

Capacity
1,536 MB
Memory type
DDR3
Bus width
192 bit
Memory clock
800 MHz
Bandwidth
38.4 GB/s

Compute

CUDA cores
144
SM count
3
TMUs
24
ROPs
24
FP32
414.72 GFLOPS
Pixel fill rate
17.28 GP/s
Texture fill rate
17.28 GT/s

Clocks

Boost clock
720 MHz

Board

TDP
75 W
Bus interface
PCIe 2.0 x16
External power required
No
Form factor
desktop

Physical

Architecture
Fermi (derived from codename prefix)
Codename
GF116-150-A1
Process
40 nm
Transistors
1.17 billion
Die size
238 mm²
Series
GeForce GT
Launch date
April 24, 2012

Not recorded by the source: generation, base clock, fp64 and launch msrp.

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.

238 mm² die · 144 shadersDie area drawn to scale against the catalog maximum of 1,540 square millimeters. Each dot = 1 shader.238 mm² die · 144 shadersEach dot = 1 shaderDashed frame = largest catalog die (1,540 mm²)

Within its series, the GeForce GT 640 OEM Rebrand ranks 19th of 54 for FP32 throughput and 29th of 94 for memory capacity. Its 75 W TDP is within the 75 W PCIe slot-power ceiling.

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