Feex·GPU
NVIDIA · GeForce

NVIDIA GeForce MX570

The NVIDIA GeForce MX570 is a graphics card released on March 1, 2022, built on the Ampere architecture using a 8 nm process. It has 2,048 shading units, 4 GB of GDDR6 memory on a 64-bit bus, 96.0 GB/s of memory bandwidth, a boost clock of 1.48 GHz and a 45 W board power rating. It scores 5,736 in the PassMark G3D benchmark. It supports DirectX 12, OpenGL 4.6 and Vulkan 1.3.

AmpereGA107 (GN20-S5-A1)8 nm
10/10 key specs recorded · 47 facts

Depth: 35 recorded fields, 6 features, 5 PassMark workloads

Specification data last verified August 11, 2026 against PassMark Videocard Benchmark, NanoReview (Firecrawl extract), NVIDIA Developer: Video Encode and Decode GPU Support Matrix and Wikipedia GPU list tables (wikigrid-2026-09). Coverage: 10 of 10 tracked specifications recorded.

Shading units
2,048cores
16 SMs
Memory
4 GB
GDDR6 · 64-bit
Boost clock
1.48 GHz
1.16 GHz base
Board power
45 W

Performance

The NVIDIA GeForce MX570 scores 5,736 in the PassMark G3D benchmark, higher than 82.4% of the 2,658 GPUs benchmarked (PassMark rank #483), measured across 52 submitted results. Its PassMark G2D score is 380.

PassMark G3D Mark
5,736
Rank #483
Faster than 82.4% of 2,658 GPUs
52 samples
0relative to the fastest GPU on record (41,928)

PassMark workload tests

DirectX 9 72 fps reference: fastest recorded 526 fps · faster than 68.5% of 1,675 GPUs
DirectX 10 31 fps reference: fastest recorded 231 fps · faster than 67.7% of 1,602 GPUs
DirectX 11 38 fps reference: fastest recorded 362 fps · faster than 64.4% of 1,430 GPUs
DirectX 12 30 fps reference: fastest recorded 213 fps · faster than 66.1% of 1,274 GPUs
GPU Compute 2,510 ops/s reference: fastest recorded 26,591 ops/s · faster than 69.4% 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 MX570 averages DirectX 9 72 fps, DirectX 10 31 fps, DirectX 11 38 fps, DirectX 12 30 fps and GPU Compute 2,510 ops/s, across 52 submitted results. Frames per second are PassMark test-scene rates, not game frame rates.

As stated by PassMark

First benchmarked 2022-06-27
Samples 52

PassMark listing (collected 2026-10-01)

Not to be confused with

This page covers the NVIDIA GeForce MX570 specifically. It is a different product from NVIDIA GeForce MX570 A, which have their own specifications. Check the exact model name before comparing figures.

Graphics processor

Architecture Ampere
Codename GA107 (GN20-S5-A1)
Chip Not recorded
Process node 8 nm
Transistors 8,700 M
Die size 200 mm²

The NVIDIA GeForce MX570 is based on the Ampere architecture, uses the GA107 (GN20-S5-A1) graphics processor, is manufactured on a 8 nm process, contains 8,700 million transistors and has a die size of 200 mm².

Shader configuration

Shading units 2,048
Compute units Not recorded
Streaming multiprocessors 16
Execution units Not recorded
Texture units (TMUs) 64
Render output units (ROPs) 40
Ray tracing cores 16
Tensor / AI cores 64
XMX engines Not recorded
Infinity cache Not recorded

The NVIDIA GeForce MX570 has 2,048 shading units, 16 streaming multiprocessors, 64 texture mapping units, 40 render output units, 16 ray tracing cores and 64 tensor cores.

The NVIDIA GeForce MX570 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 MX570.

Clock speeds

Base clock 1.16 GHz
Boost clock 1.48 GHz
Game clock Not recorded
Memory clock 1.50 GHz
Effective memory clock Not recorded

The NVIDIA GeForce MX570 runs at a base clock of 1.16 GHz and boosts to 1.48 GHz.

Memory

Size 4 GB
Type GDDR6
Bus width 64-bit
Bandwidth 96.0 GB/s

The NVIDIA GeForce MX570 is equipped with 4 GB of GDDR6 memory, uses a 64-bit memory bus and delivers 96.0 GB/s of memory bandwidth.

Board and power

The NVIDIA GeForce MX570 has a board power rating of 45 W.

Board power (TDP) 45 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 Not recorded

Market

Launched March 1, 2022
Launch price Not recorded
Status Not recorded
Form factor Not recorded
Segment Desktop
Series GeForce

The NVIDIA GeForce MX570 was released on March 1, 2022.

Benchmarks

PassMark G3D 5,736
PassMark G2D 380
Rank #483
Samples 52

Graphics and compute APIs

The NVIDIA GeForce MX570 supports DirectX 12, OpenGL 4.6 and Vulkan 1.3.

DirectX 12
OpenGL 4.6
Vulkan 1.3

Feex has no recorded CUDA compute capability for the NVIDIA GeForce MX570. Feex has no recorded OpenCL version for the NVIDIA GeForce MX570.

Features

The NVIDIA GeForce MX570 has 2 supported features recorded outside the media engine. A feature that no source mentions is shown as not listed, never as unsupported.

Rendering

  • Supported: Hardware ray tracing
    Dedicated GPU hardware that speeds up ray-traced lighting, reflections and shadows in supported games and apps.
    Ray tracing units: 16
Not listed (3)

No source Feex holds states whether the NVIDIA GeForce MX570 supports DirectX 12 Ultimate, NVIDIA DLSS and Vulkan ray tracing. That is silence, not a statement that they are unsupported.

The NVIDIA GeForce MX570 supports Hardware ray tracing under Rendering.

Compute and AI

  • Supported: Tensor cores
    NVIDIA's dedicated matrix-math units used for AI workloads such as DLSS and machine-learning inference.
    Tensor cores: 64
Not listed (2)

No source Feex holds states whether the NVIDIA GeForce MX570 supports CUDA and NVLink / SLI. That is silence, not a statement that they are unsupported.

The NVIDIA GeForce MX570 supports Tensor cores under Compute and AI.

Media engine

The NVIDIA GeForce MX570 provides hardware encode for H.264 (AVC) and HEVC (H.265). It does not support hardware encode for AV1.

NVIDIA NVENC encoder 7th Generation Encoder engines: 1NVIDIA's dedicated video-encoding engine, used by streaming and capture software; newer generations encode more efficiently.
Hardware video codec support of the NVIDIA GeForce MX570
CodecEncodeDecode
H.264 (AVC) Supported4:4:4: YesNot stated by the vendor
HEVC (H.265) Supported4:2:2: No; 4:4:4: Yes; 10-bit: Yes; B-frames: Yes; 8K: YesNot stated by the vendor
AV1 Not supportedNot stated by the vendor

supported   explicitly not supported   not stated by the vendor

Not listed: VP9. No source Feex holds states whether the NVIDIA GeForce MX570 supports this codec; that is silence, not a statement that it is unsupported.

Media engines recorded for the NVIDIA GeForce MX570: NVIDIA NVENC encoder (7th Generation, encoder engines: 1).

Naming and aliases

The NVIDIA GeForce MX570 is also known by other names: PassMark also lists it as NVIDIA GeForce MX570 (Mobile).

Other names (PassMark) NVIDIA GeForce MX570 (Mobile)

Frequently asked questions

How much VRAM does the NVIDIA GeForce MX570 have?

The NVIDIA GeForce MX570 has 4 GB of GDDR6 memory on a 64-bit bus. Its memory bandwidth is 96.0 GB/s.

How much power does the NVIDIA GeForce MX570 use and what power supply does it need?

The NVIDIA GeForce MX570 has a board power rating of 45 W.

How fast is the NVIDIA GeForce MX570?

The NVIDIA GeForce MX570 scores 5,736 in the PassMark G3D benchmark, higher than 82.4% of the 2,658 GPUs benchmarked. Its PassMark rank is #483. In the PassMark DirectX 12 test it averages 30 fps.

Does the NVIDIA GeForce MX570 support ray tracing?

Yes. The NVIDIA GeForce MX570 has hardware ray tracing with 16 ray tracing cores.

Does the NVIDIA GeForce MX570 support AV1 encoding?

No. Feex records AV1 hardware encoding as explicitly not supported on the NVIDIA GeForce MX570.

When was the NVIDIA GeForce MX570 released?

The NVIDIA GeForce MX570 was released on March 1, 2022.

Corrections to this record

After an audit, 1 value on the NVIDIA GeForce MX570 record was corrected. Each change is listed with its old value, new value, rule and sources.

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

Similar performance