Apple A18 Pro GPU vs Adreno X2-90

We compared two integrated laptop GPUs: the Apple A18 Pro GPU with 128 pipelines and 768 shaders against the 1 year and 1 month newer Adreno X2-90 that utilizes 12 pipelines and 2048 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

Review

General comparison of performance in games, applications, power efficiency, and other metrics
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score

Key differences

Key distinctions and advantages of Adreno X2-90 over A18 Pro GPU
Reasons to consider the Adreno X2-90
  • Performs significantly better (up to 2.9x) in 3DMark Steel Nomad Lite
  • 3.3x higher maximum theoretical performance (7.6 vs 2.3 TFLOPS)
  • Has 2.7x more shading units (2048 vs 768)

Benchmarks

Graphics cards’ performance in recent benchmarking apps

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
Adreno X2-90 +187%
5142
Time Spy - 3782
Solar Bay 7374 24300
Port Royal - 1592
Fire Strike - 10039
Wild Life Extreme 3947 9890
Night Raid - 57486
Sources: 3DMark [1], [2]

GeekBench 6 GPU Compute

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
Background Blur 57.1 img/sec -
Face Detection 91.4 img/sec -
Horizon Detection 0.92 Gpixels/sec -
Edge Detection 1.21 Gpixels/sec -
Gaussian Blur 1.5 Gpixels/sec -
Feature Matching 0.45 Gpixels/sec -
Stereo Matching 84.2 Gpixels/sec -
Particle Physics 3061 FPS -
API Metal -
Sources: Geekbench [3]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
G2D Mark - 592
DirectX 11 - 57 FPS
DirectX 12 - 29 FPS
GPU Compute - 3638 Ops/s
Sources: PassMark [5] – 61 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Apple A18 Pro GPU
DateBenchmarkResult
📘 2026-04-24 -> RennsportGeekbench 6 OpenCL19670
Adreno X2-90
No benchmark results yet

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
Image Classification (SP) 3264 -
Image Segmentation (HP) 4550 -
Image Super Resolution (Q) 6705 -
Face Detection (HP) 11770 -
Pose Estimation (Q) 15548 -
Text Classification (SP) 3678 -
Machine Translation (HP) 5678 -
Object Detection (SP) 3360 -
Depth Estimation (Q) 13468 -
Style Transfer (SP) 31541 -
Framework Core ML -
Backend GPU -
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Apple A18 Pro GPU and Adreno X2-90

General

Vendor Apple Qualcomm
Build Integrated Integrated
Released September 9, 2024 September 25, 2025
Case Laptop Laptop
Purpose Generic Generic
Segment Mid-range Mid-range
Architecture Apple M GPU Adreno X2
GPU Codename Custom Adreno X2
Rival Equivalent - - Apple M4 Max GPU (40-core)
Recommended CPU - Apple A18 Pro (MacBook) or above - Qualcomm Snapdragon X2 Elite Extreme (X2E-96-100) or above
Used in CPUs - Apple A18 Pro (MacBook) - Qualcomm Snapdragon X2 Elite (X2E-90-100)
- Qualcomm Snapdragon X2 Elite (X2E-88-100)
- Qualcomm Snapdragon X2 Elite Extreme (X2E-94-100)
- Qualcomm Snapdragon X2 Elite Extreme (X2E-96-100)
Laptop GPU ranking (81st and 34th place)

Graphics Processing Unit

Base Clock - 500 MHz
Boost Clock 1490 MHz 1700-1850 MHz (configurable)
Shading Units 768 2048
Texture Mapping Units (TMUs) 40 128
Render Output Units (ROPs) - 64
Compute Units (Pipelines) 128 12
Tensor Cores - No
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate - 109-118 GPixel/s
Texture Fill Rate 60 GTexel/s 218-237 GTexel/s
FLOPS (FP32)
2.3 TFLOPS
Adreno X2-90 +230%
7-7.6 TFLOPS

Physical

Interface Custom IGP
Manufacturing TSMC TSMC
Fabrication Process 3 nm 3 nm
Die Size - 220 mm²

Memory

Memory Type System Shared System Shared
Memory Clock 7500 MHz -
Bus 128-bit 192-bit
ECC No No
Memory Bandwidth
228 GB/s

API

DirectX - 12.2
Vulkan - 1.4
OpenCL - 3.0
CUDA - No
Ray Tracing Yes Yes
DLSS No No
DisplayPort - 1.4

Cast your vote

Choose between two graphics cards
0 (0%)
2 (100%)
Total votes: 2

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of NanoReview community!