NVIDIA · GeForce GTX

NVIDIA GeForce GTX 870M

The NVIDIA GeForce GTX 870M is a graphics card released on March 12, 2014, built on the Kepler architecture. It has 6 GB of GDDR5 memory on a 192-bit bus, 120.0 GB/s of memory bandwidth and a 110 W board power rating. It scores 3,557 in the PassMark G3D benchmark. It supports DirectX 12, OpenGL 4.5, Vulkan 1.2 and CUDA compute capability 3.0.

Kepler1344:112:24 (7 SMX)

8/10 key specs recorded · 24 facts

Depth: 35 recorded fields, 1 feature, 5 PassMark workloads

Specification data last verified October 1, 2026 against PassMark Videocard Benchmark and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 8 of 10 tracked specifications recorded.

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

Shading units

n/a

Memory

6 GB

GDDR5 · 192-bit

Boost clock

n/a

Board power

110 W

Performance

The NVIDIA GeForce GTX 870M scores 3,557 in the PassMark G3D benchmark, higher than 75.2% of the 2,658 GPUs benchmarked (PassMark rank #688), measured across 735 submitted results. Its PassMark G2D score is 279.

PassMark G3D Mark

3,557

Rank #688
Faster than 75.2% of 2,658 GPUs
735 samples

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

PassMark workload tests

DirectX 9 67 fps

reference: fastest recorded 526 fps · faster than 66.6% of 1,675 GPUs

DirectX 10 15 fps

reference: fastest recorded 231 fps · faster than 56.6% of 1,602 GPUs

DirectX 11 31 fps

reference: fastest recorded 362 fps · faster than 60.5% of 1,430 GPUs

DirectX 12 13 fps

reference: fastest recorded 213 fps · faster than 43.7% of 1,274 GPUs

GPU Compute 1,649 ops/s

reference: fastest recorded 26,591 ops/s · faster than 60.9% 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 870M averages DirectX 9 67 fps, DirectX 10 15 fps, DirectX 11 31 fps, DirectX 12 13 fps and GPU Compute 1,649 ops/s, across 735 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

As stated by PassMark

Category Mobile

Bus interface PCIe 3.0 x16

Max memory 6 GB

Core clock 967 MHz

Memory clock 2500 MHz

DirectX 11

OpenGL 4.5

Max TDP 110 W

First benchmarked 2014-03-09

Samples 735

PassMark listing (collected 2026-10-01)

PassMark's own listing for the NVIDIA GeForce GTX 870M states the PCIe 3.0 x16 interface, up to 6 GB of memory, a core clock of 967 MHz, DirectX 11 and OpenGL 4.5, first benchmarked on 2014-03-09. These are PassMark's figures, shown separately from the specification tables above.

Graphics processor

Architecture Kepler

Codename 1344:112:24 (7 SMX)

Chip Not recorded

Process node Not recorded

Transistors Not recorded

Die size Not recorded

The NVIDIA GeForce GTX 870M is based on the Kepler architecture and uses the 1344:112:24 (7 SMX) graphics processor.

Memory

Size 6 GB

Type GDDR5

Bus width 192-bit

Bandwidth 120.0 GB/s

The NVIDIA GeForce GTX 870M is equipped with 6 GB of GDDR5 memory, uses a 192-bit memory bus and delivers 120.0 GB/s of memory bandwidth.

Board and power

The NVIDIA GeForce GTX 870M has a board power rating of 110 W and it connects over PCIe 3.0 x16.

Board power (TDP) 110 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 3.0 x16

Market

Launched March 12, 2014

Launch price Not recorded

Status Not recorded

Form factor Not recorded

Segment Desktop

Series GeForce GTX

The NVIDIA GeForce GTX 870M was released on March 12, 2014.

Benchmarks

PassMark G3D 3,557

PassMark G2D 279

Rank #688

Samples 735

Graphics and compute APIs

The NVIDIA GeForce GTX 870M supports DirectX 12, OpenGL 4.5, Vulkan 1.2 and CUDA compute capability 3.0.

DirectX 12

OpenGL 4.5

Vulkan 1.2

CUDA compute capability 3.0

Feex has no recorded OpenCL version for the NVIDIA GeForce GTX 870M.

Features

The NVIDIA GeForce GTX 870M has 1 supported feature recorded outside the media engine. A feature that no source mentions is shown as not listed, never as unsupported.

Compute and AI

Supported: CUDA Compute capability 3.0

Support for NVIDIA's CUDA computing platform, used by many creative, scientific and AI applications.

Not listed (2)

No source Feex holds states whether the NVIDIA GeForce GTX 870M supports Tensor cores and NVLink / SLI. That is silence, not a statement that they are unsupported.

The NVIDIA GeForce GTX 870M supports CUDA (Compute capability 3.0) under Compute and AI.

Naming and aliases

The NVIDIA GeForce GTX 870M is also known by other names: PassMark also lists it as NVIDIA GeForce GTX 870M (Mobile).

Other names (PassMark) NVIDIA GeForce GTX 870M (Mobile)

Frequently asked questions

How much VRAM does the NVIDIA GeForce GTX 870M have?

The NVIDIA GeForce GTX 870M has 6 GB of GDDR5 memory on a 192-bit bus. Its memory bandwidth is 120.0 GB/s.

How much power does the NVIDIA GeForce GTX 870M use and what power supply does it need?

The NVIDIA GeForce GTX 870M has a board power rating of 110 W.

How fast is the NVIDIA GeForce GTX 870M?

The NVIDIA GeForce GTX 870M scores 3,557 in the PassMark G3D benchmark, higher than 75.2% of the 2,658 GPUs benchmarked. Its PassMark rank is #688. In the PassMark DirectX 12 test it averages 13 fps.

What is the CUDA compute capability of the NVIDIA GeForce GTX 870M?

The NVIDIA GeForce GTX 870M has CUDA compute capability 3.0.

What bus interface does the NVIDIA GeForce GTX 870M use?

The NVIDIA GeForce GTX 870M connects over PCIe 3.0 x16.

When was the NVIDIA GeForce GTX 870M released?

The NVIDIA GeForce GTX 870M was released on March 12, 2014.

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: Kepler (was Not recorded). Rule: Architecture from chip codename. chip GK104 -> Kepler. 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.