Apple M3 Max GPU (40-core) vs A18 Pro GPU

We compared two integrated laptop graphics cards: the Apple M3 Max GPU (40-core) with 640 pipelines and 5120 shaders against the 10 months newer A18 Pro GPU that utilizes 128 pipelines and 768 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
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
DeviceFacts Final Score
Overall video card score

Key differences

Key distinctions and advantages of A18 Pro GPU over M3 Max GPU (40-core)
Reasons to consider the Apple M3 Max GPU (40-core)
  • Performs significantly better (up to 6.9x) in 3DMark Steel Nomad Lite
  • 6.1x higher maximum theoretical performance (14.1 vs 2.3 TFLOPS)
  • Has 6.7x more shading units (5120 vs 768)
  • Achieves 3x more points in the GeekBench 6 Compute test (94K vs 31K)

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
Solar Bay 49656 7365
Wild Life Extreme 30893 3949
Sources: 3DMark [1], [2]

GeekBench 6 GPU Compute

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
94528
31229
Background Blur 157.6 img/sec 57.1 img/sec
Face Detection 100.9 img/sec 91.4 img/sec
Horizon Detection 3.99 Gpixels/sec 0.92 Gpixels/sec
Edge Detection 6.04 Gpixels/sec 1.21 Gpixels/sec
Gaussian Blur 5 Gpixels/sec 1.5 Gpixels/sec
Feature Matching 0.84 Gpixels/sec 0.45 Gpixels/sec
Stereo Matching 363.8 Gpixels/sec 84.2 Gpixels/sec
Particle Physics 12226.9 FPS 3061 FPS
API OpenCL Metal
Sources: Geekbench [3], [4]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU

Blender

Rendering performance test for 3D modeling
Blender GPU
Sources: Blender [9] – 446 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Apple M3 Max GPU (40-core)
No benchmark results yet
Apple A18 Pro GPU
DateBenchmarkResult
📘 2026-10-03 -> RennsportGeekbench 7 OpenCL18863
📘 2026-04-24 -> RennsportGeekbench 6 OpenCL19670

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) 8685 3264
Image Segmentation (HP) 20739 4550
Image Super Resolution (Q) 22775 6705
Face Detection (HP) 37676 11770
Pose Estimation (Q) 91609 15548
Text Classification (SP) 2909 3678
Machine Translation (HP) 5274 5678
Object Detection (SP) 7480 3360
Depth Estimation (Q) 38212 13468
Style Transfer (SP) 190681 31541
Framework Core ML Core ML
Backend GPU GPU
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Apple M3 Max GPU (40-core) and A18 Pro GPU

General

Vendor Apple Apple
Build Integrated Integrated
Released October 31, 2023 September 9, 2024
Case Laptop Laptop
Purpose Professional Generic
Segment High-end Mid-range
Architecture Apple M GPU Apple M GPU
GPU Codename - Custom
Rival Equivalent - GeForce RTX 4070 Laptop -
Successor - Apple M5 Max GPU (40-core) -
Recommended CPU - Apple M3 Max or above - Apple A18 Pro (MacBook) or above
Used in CPUs - Apple M3 Max - Apple A18 Pro (MacBook)
Laptop GPU ranking (21st and 83rd place)

Graphics Processing Unit

Base Clock 500 MHz -
Boost Clock 1380 MHz 1490 MHz
Shading Units 5120 768
Texture Mapping Units (TMUs) 320 40
Render Output Units (ROPs) 160 -
Compute Units (Pipelines) 640 128
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 221 GPixel/s -
Texture Fill Rate 442 GTexel/s 60 GTexel/s
FLOPS (FP32)
14.1 TFLOPS
2.3 TFLOPS

Physical

Interface Custom Custom
TGP 60 W -
Manufacturing TSMC TSMC
Fabrication Process 3 nm 3 nm
Transistor Count 56 billion -
Max. Temperature 100°C -

Memory

Memory Type System Shared System Shared
Memory Clock 6400 MHz 7500 MHz
Effective Memory Speed 12800 Mbps -
Bus 512-bit 128-bit
ECC No No
Memory Bandwidth

API

Ray Tracing Yes Yes
DLSS No No

Cast your vote

Choose between two graphics cards
0 (0%)
0 (0%)
Total votes: < 1

User opinions

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