Apple M2 Max GPU (38-core)
38B
Memory TypeSystem Shared
Boost Clock1398 MHz
TGP70 W
ArchitectureApple M GPU
Benchmarks
Gaming26
Render39
Energy75
TFLOPS (FP32)13.6
Geekbench OpenCL86,936
Steel Nomad Lite Score9413
GB6 Compute Score86,936
Cinebench 2024 GPU5533
Blender GPU1776.37
GB6 ML Single Precision15,005
GB6 ML Half Precision16,456
GB6 ML Quantized15,418
FLOPS (FP32)13.6 TFLOPS
Memory Bandwidth409.6 GB/s
Full specifications
3D Mark
Solar Bay
30368
Wild Life Extreme
24948
GeekBench 6 OpenCL
Background Blur
149 img/sec
Face Detection
98.1 img/sec
Horizon Detection
3.8 Gpixels/sec
Edge Detection
6.88 Gpixels/sec
Gaussian Blur
4.44 Gpixels/sec
Feature Matching
0.73 Gpixels/sec
Stereo Matching
264.9 Gpixels/sec
Particle Physics
11144.2 FPS
API
OpenCL
GeekBench 6 ML
Image Classification (SP)
6657
Image Segmentation (HP)
13854
Image Super Resolution (Q)
18642
Face Detection (HP)
27965
Pose Estimation (Q)
83144
Text Classification (SP)
2377
Machine Translation (HP)
2052
Object Detection (SP)
6495
Depth Estimation (Q)
31105
Style Transfer (SP)
135686
Framework
Core ML
Backend
GPU
General
Vendor
Apple
Build
Integrated
Released
January 17, 2023
Case
Laptop
Purpose
Professional
Segment
High-end
Architecture
Apple M GPU
Nvidia Equivalent
- GeForce RTX 3060 Laptop
Successor
- Apple M5 Max GPU (40-core)
Used in CPUs
- Apple M2 Max
Graphics Processing Unit
Base Clock
450 MHz
Boost Clock
1398 MHz
Shading Units
4864
Texture Mapping Units (TMUs)
304
Render Output Units (ROPs)
152
Compute Units (Pipelines)
608
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
212 GPixel/s
Texture Fill Rate
425 GTexel/s
Physical
Interface
Custom
TGP
70 W
Manufacturing
TSMC
Fabrication Process
5 nm
Transistor Count
52 billion
Max. Temperature
94°C
Memory
Memory Type
System Shared
Memory Clock
6400 MHz
Effective Memory Speed
12800 Mbps
Bus
512-bit
ECC
No
API
Ray Tracing
No
DLSS
No
Specifications compiled from NanoReview. Last updated 2026-09-29.
More graphics cards
View all →67
Nvidia
GeForce RTX 5090 Laptop
- Memory24 GB
- Memory TypeGDDR7
- Boost Clock1515-2160 MHz (configurable)
- TGP95-175 W (configurable)
Laptop GPU
66
Nvidia
Nvidia RTX Pro 5000 Laptop (Blackwell)
- Memory24 GB
- Memory TypeGDDR7
- Boost Clock1680-1807 MHz (configurable)
- TGP95-175 W (configurable)
Laptop GPU
60
Nvidia
GeForce RTX 5080 Laptop
- Memory16 GB
- Memory TypeGDDR7
- Boost Clock1500-2410 MHz (configurable)
- TGP80-175 W (configurable)
Laptop GPU
59
Nvidia
GeForce RTX 4090 Laptop
- Memory16 GB
- Memory TypeGDDR6
- Boost Clock1455-2040 MHz (configurable)
- TGP80-175 W (configurable)
Laptop GPU