Apple M4 Pro GPU (20-core) vs Pro GPU (16-core)

We compared two integrated laptop professional GPUs: the Apple M4 Pro GPU (20-core) with 320 pipelines and 2560 shaders against the Pro GPU (16-core) that utilizes 256 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
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score

Key differences

Key distinctions and advantages of M4 Pro GPU (16-core) over M4 Pro GPU (20-core)
Reasons to consider the Apple M4 Pro GPU (20-core)
  • Performs slightly better (up to 16%) in 3DMark Steel Nomad Lite
  • 25% higher maximum theoretical performance (8.1 vs 6.5 TFLOPS)
  • Has 25% more shading units (2560 vs 2048)

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 33418 28734
Wild Life Extreme 19535 16471
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
Background Blur 125.1 img/sec 106 img/sec
Face Detection 80 img/sec 73.1 img/sec
Horizon Detection 2.88 Gpixels/sec 2.59 Gpixels/sec
Edge Detection 4.22 Gpixels/sec 3.8 Gpixels/sec
Gaussian Blur 2.98 Gpixels/sec 2.4 Gpixels/sec
Feature Matching 0.8 Gpixels/sec 0.73 Gpixels/sec
Stereo Matching 235 Gpixels/sec 198.6 Gpixels/sec
Particle Physics 9516.1 FPS 8166.3 FPS
API OpenCL OpenCL
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], [10]399 & 285 samples

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) 8046 7548
Image Segmentation (HP) 15443 15108
Image Super Resolution (Q) 20807 20789
Face Detection (HP) 30860 28665
Pose Estimation (Q) 56783 57124
Text Classification (SP) 2888 2888
Machine Translation (HP) 6167 6086
Object Detection (SP) 7592 6804
Depth Estimation (Q) 33607 32732
Style Transfer (SP) 126726 123465
Framework Core ML Core ML
Backend GPU GPU
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Apple M4 Pro GPU (20-core) and Pro GPU (16-core)

General

Vendor Apple Apple
Build Integrated Integrated
Released October 29, 2024 October 29, 2024
Case Laptop Laptop
Purpose Professional Professional
Segment Mid-range Mid-range
Architecture Apple M GPU Apple M GPU
GPU Codename Custom Custom
Rival Equivalent - GeForce RTX 4060 Laptop - GeForce RTX 4060 Laptop
Successor - Apple M5 Pro GPU (20-core) - Apple M5 Pro GPU (16-core)
Recommended CPU - Apple M4 Pro (14-Core) or above - Apple M4 Pro (12-Core) or above
Used in CPUs - Apple M4 Pro (14-Core) - Apple M4 Pro (12-Core)
Laptop GPU ranking (36th and 44th place)

Graphics Processing Unit

Base Clock 500 MHz 500 MHz
Boost Clock 1578 MHz 1578 MHz
Shading Units 2560 2048
Texture Mapping Units (TMUs) 160 128
Render Output Units (ROPs) 80 64
Compute Units (Pipelines) 320 256
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 126 GPixel/s 101 GPixel/s
Texture Fill Rate 252 GTexel/s 202 GTexel/s
FLOPS (FP32)
8.1 TFLOPS

Physical

Interface Custom Custom
TGP 26 W 26 W
Manufacturing TSMC TSMC
Fabrication Process 3 nm 3 nm
Max. Temperature 100°C 100°C

Memory

Memory Type System Shared System Shared
Memory Clock 8533 MHz 8533 MHz
Effective Memory Speed 15000 Mbps 15000 Mbps
Bus 192-bit 192-bit
ECC No No
Memory Bandwidth

API

Ray Tracing Yes Yes
DLSS No No

Cast your vote

Choose between two graphics cards
62 (51.2%)
59 (48.8%)
Total votes: 121

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of NanoReview community!
Avatar
User373 November 18, 2024 at 12:16 AM
Don't get the 20 core GPU if you want sustained gaming performance. In addition to the extra 4 GPU cores, it also has an additional 2 CPU (performance) cores, it also runs hotter, has a higher TGP (+6 watts) and will throttle much more than the binned version under sustained gaming load. In hour long (or more) gaming sessions you can expect the extra heat created by the extra CPU cores and extra GPU cores to eat into the gaming performance lead the 20 core GPU has over the 16. So far the 16 core variant isn't showing the same kind of throttling impact the 20 core does.
+42 Reply
Avatar
MacInTosh March 11, 2025 at 12:41 PM
--> Just make the fans run a bit faster. The extra performance gains are about 7-15%. You should generally make the fans run faster while gaming (2500 to 3000). You can use Macs Fan Control for example. Also, in the M4 Pro Mac Mini, the thermals are way better, so keep that in mind.
+1 Reply
Avatar
User372 November 6, 2024 at 03:41 PM
If you have the extra money, get the 20-core GPU. It is an additional $200, and 25% more of 1399 (the base price of the Mac Mini, M4 Pro). $350 is 25% more than 1399, and Apple only charges $200, making this good value. If you have the extra money, spend it, it will be worth it.
+34 Reply
Avatar
User234 November 15, 2024 at 05:36 PM
How it can be worth it when the benchmarks show results within margin error the same performance?
+51 Reply