NVIDIA · GeForce GTX

NVIDIA GeForce GTX 580M

The NVIDIA GeForce GTX 580M is a graphics card released on June 28, 2011, built on the Fermi architecture. It has 384 shading units, 2 GB of GDDR5 memory on a 256-bit bus, 96.0 GB/s of memory bandwidth, a boost clock of 620 MHz and a 100 W board power rating. It scores 1,851 in the PassMark G3D benchmark. It supports DirectX 12 and OpenGL 4.6.

FermiGF114

9/10 key specs recorded · 27 facts

Depth: 37 recorded fields, 5 PassMark workloads

Specification data last verified October 1, 2026 against PassMark Videocard Benchmark and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 9 of 10 tracked specifications recorded.

PassMark Videocard Benchmark Wikipedia GPU list tables (wikigrid-2026-09)PassMark Videocard Benchmark

Shading units

384cores

Memory

2 GB

GDDR5 · 256-bit

Boost clock

n/a

620 MHz base

Board power

100 W

Performance

The NVIDIA GeForce GTX 580M scores 1,851 in the PassMark G3D benchmark, higher than 64.6% of the 2,658 GPUs benchmarked (PassMark rank #1,047), measured across 106 submitted results. Its PassMark G2D score is 334.

PassMark G3D Mark

1,851

Rank #1,047
Faster than 64.6% of 2,658 GPUs
106 samples

0relative to the fastest GPU on record (41,928)

PassMark workload tests

DirectX 9 44 fps

reference: fastest recorded 526 fps · faster than 55.3% of 1,675 GPUs

DirectX 10 8 fps

reference: fastest recorded 231 fps · faster than 45.3% of 1,602 GPUs

DirectX 11 17 fps

reference: fastest recorded 362 fps · faster than 46.4% of 1,430 GPUs

DirectX 12 7 fps

reference: fastest recorded 213 fps · faster than 24.3% of 1,274 GPUs

GPU Compute 617 ops/s

reference: fastest recorded 26,591 ops/s · faster than 33.1% of 1,447 GPUs

Averages of PassMark PerformanceTest submissions; frames/sec are PassMark test-scene rates, not game FPS. Tests PassMark does not report for this card are omitted. PassMark listing

In the PassMark workload tests the NVIDIA GeForce GTX 580M averages DirectX 9 44 fps, DirectX 10 8 fps, DirectX 11 17 fps, DirectX 12 7 fps and GPU Compute 617 ops/s, across 106 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

As stated by PassMark

Category Mobile

Bus interface PCIe 2.0 x16

Max memory 2 GB

Core clock 620 MHz

Memory clock 3000 MHz

DirectX 11

OpenGL 4.5

Max TDP 100 W

First benchmarked 2011-07-29

Samples 106

PassMark listing (collected 2026-10-01)

PassMark's own listing for the NVIDIA GeForce GTX 580M states the PCIe 2.0 x16 interface, up to 2 GB of memory, a core clock of 620 MHz, DirectX 11 and OpenGL 4.5, first benchmarked on 2011-07-29. These are PassMark's figures, shown separately from the specification tables above.

Graphics processor

Architecture Fermi

Codename GF114

Chip Not recorded

Process node Not recorded

Transistors Not recorded

Die size Not recorded

The NVIDIA GeForce GTX 580M is based on the Fermi architecture and uses the GF114 graphics processor.

Shader configuration

Shading units 384

Compute units Not recorded

Streaming multiprocessors Not recorded

Execution units Not recorded

Texture units (TMUs) 64

Render output units (ROPs) 32

Ray tracing cores Not recorded

Tensor / AI cores Not recorded

XMX engines Not recorded

Infinity cache Not recorded

The NVIDIA GeForce GTX 580M has 384 shading units, 64 texture mapping units and 32 render output units.

The NVIDIA GeForce GTX 580M does not use XMX engines; those are specific to Intel Arc graphics. Infinity Cache is an AMD architectural feature and does not apply to the NVIDIA GeForce GTX 580M. Feex has no recorded ray tracing core count for the NVIDIA GeForce GTX 580M.

Clock speeds

Base clock 620 MHz

Boost clock Not recorded

Game clock Not recorded

Memory clock Not recorded

Effective memory clock Not recorded

The NVIDIA GeForce GTX 580M runs at a base clock of 620 MHz.

Memory

Size 2 GB

Type GDDR5

Bus width 256-bit

Bandwidth 96.0 GB/s

The NVIDIA GeForce GTX 580M is equipped with 2 GB of GDDR5 memory, uses a 256-bit memory bus and delivers 96.0 GB/s of memory bandwidth.

Board and power

The NVIDIA GeForce GTX 580M has a board power rating of 100 W and it connects over PCIe 2.0 x16.

Board power (TDP) 100 W

Total board power Not recorded

Suggested PSU Not recorded

Power connectors Not recorded

Slot width Not recorded

Length Not recorded

Width Not recorded

Height Not recorded

Cooler Not recorded

Max temperature Not recorded

Bus interface PCIe 2.0 x16

Market

Launched June 28, 2011

Launch price Not recorded

Status Not recorded

Form factor Not recorded

Segment Desktop

Series GeForce GTX

The NVIDIA GeForce GTX 580M was released on June 28, 2011.

Benchmarks

PassMark G3D 1,851

PassMark G2D 334

Rank #1,047

Samples 106

Graphics and compute APIs

The NVIDIA GeForce GTX 580M supports DirectX 12 and OpenGL 4.6.

DirectX 12

OpenGL 4.6

Feex has no recorded CUDA compute capability for the NVIDIA GeForce GTX 580M. Feex has no recorded Vulkan version for the NVIDIA GeForce GTX 580M. Feex has no recorded OpenCL version for the NVIDIA GeForce GTX 580M.

Naming and aliases

The NVIDIA GeForce GTX 580M is also known by other names: PassMark also lists it as NVIDIA GeForce GTX 580M (Mobile).

Other names (PassMark) NVIDIA GeForce GTX 580M (Mobile)

Frequently asked questions

How much VRAM does the NVIDIA GeForce GTX 580M have?

The NVIDIA GeForce GTX 580M has 2 GB of GDDR5 memory on a 256-bit bus. Its memory bandwidth is 96.0 GB/s.

How much power does the NVIDIA GeForce GTX 580M use and what power supply does it need?

The NVIDIA GeForce GTX 580M has a board power rating of 100 W.

How fast is the NVIDIA GeForce GTX 580M?

The NVIDIA GeForce GTX 580M scores 1,851 in the PassMark G3D benchmark, higher than 64.6% of the 2,658 GPUs benchmarked. Its PassMark rank is #1,047. In the PassMark DirectX 12 test it averages 7 fps.

What bus interface does the NVIDIA GeForce GTX 580M use?

The NVIDIA GeForce GTX 580M connects over PCIe 2.0 x16.

When was the NVIDIA GeForce GTX 580M released?

The NVIDIA GeForce GTX 580M was released on June 28, 2011.

Corrections to this record

After an audit, 1 empty field was filled from sources. Each change is listed with its old value, new value, rule and sources.

1 filled value

Architecture: Fermi (was Not recorded). Rule: Architecture from chip codename. chip GF114 -> Fermi. Sources: Wikipedia: List of Nvidia graphics processing units (revision 1377107724).

The audit log is public: all changes for this GPU, the corrections overview and the method.