Apple M5 Ultra GPU (64-core) vs Max GPU (40-core)

We performed a head-to-head comparison of the Apple M5 Ultra GPU (64-core) with 1024 pipelines and 8192 shaders against the 6 months older Max GPU (40-core) that utilizes 640 pipelines and 5120 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
Scores marked with a red asterisk (**) represent initial estimates from early testing.
The "Energy Efficiency" metric has less impact on the NanoReview Score for desktop GPU.

Key differences

Key distinctions and advantages of M5 Max GPU (40-core) over M5 Ultra GPU (64-core)
Reasons to consider the Apple M5 Ultra GPU (64-core)
  • 60% higher maximum theoretical performance (26.5 vs 16.6 TFLOPS)
  • Has 2x higher memory bandwidth: 1228.8 vs 614 GB/s
  • Has 60% more shading units (8192 vs 5120)

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 - 79263
Wild Life Extreme - 42423
Sources: 3DMark [1]

GeekBench 6 GPU Compute

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
Background Blur - 257 img/sec
Face Detection - 182.1 img/sec
Horizon Detection - 5.4 Gpixels/sec
Edge Detection - 8.33 Gpixels/sec
Gaussian Blur - 8.86 Gpixels/sec
Feature Matching - 1.28 Gpixels/sec
Stereo Matching - 455.4 Gpixels/sec
Particle Physics - 21658 FPS
API - OpenCL
Sources: Geekbench [3]

Cinebench 2024 GPU

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

Blender

Rendering performance test for 3D modeling
Sources: Blender [9]201 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Apple M5 Ultra GPU (64-core)
No benchmark results yet
Apple M5 Max GPU (40-core)
DateBenchmarkResult
📘 2026-04-16 -> Apple loverGeekBench146276
📘 2026-03-25 (Steven)Cinebench 20249283
📘 2026-03-25 (Steven)Steel Nomad Light18486

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) - 10711
Image Segmentation (HP) - 42406
Image Super Resolution (Q) - 42905
Face Detection (HP) - 73489
Pose Estimation (Q) - 289766
Text Classification (SP) - 6087
Machine Translation (HP) - 8881
Object Detection (SP) - 10130
Depth Estimation (Q) - 84224
Style Transfer (SP) - 264552
Framework - Core ML
Backend - GPU
Sources: Geekbench [9]

Specifications

Technical specifications of Apple M5 Ultra GPU (64-core) and Max GPU (40-core)

General

Vendor Apple Apple
Build Integrated Integrated
Released August 25, 2026 March 3, 2026
Case Desktop Laptop
Purpose Professional Professional
Segment High-end Mid-range
Architecture Apple M GPU Apple M GPU
GPU Codename Custom Custom
Rival Equivalent - GeForce RTX 5080 -
Recommended CPU - Apple M5 Ultra (30-Core) or above - Apple M5 Max (40-сore GPU) or above
Used in CPUs - Apple M5 Ultra (30-Core) - Apple M5 Max (40-сore GPU)
Desktop GPU rating (#22nd place)
Laptop GPU ranking (#6th place)

Graphics Processing Unit

Base Clock 500 MHz -
Boost Clock 1620 MHz 1620 MHz
Shading Units 8192 5120
Texture Mapping Units (TMUs) 640 320
Render Output Units (ROPs) 320 160
Compute Units (Pipelines) 1024 640
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 518 GPixel/s 259 GPixel/s
Texture Fill Rate 1037 GTexel/s 518 GTexel/s
FLOPS (FP32)
26.5 TFLOPS
16.6 TFLOPS

Physical

Interface Custom Custom
Manufacturing TSMC TSMC
Fabrication Process 3 nm 3 nm
Transistor Count - 28 billion
Max. Temperature - 100°C

Memory

Memory Type System Shared System Shared
Memory Clock 9600 MHz 9600 MHz
Bus 1024-bit 512-bit
ECC No No
Memory Bandwidth
1228.8 GB/s

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 NanoReview community!