Home > GPU Comparison > RTX 5090 vs M4 Ultra GPU (80-core) – what's better?

GeForce RTX 5090 vs Apple M4 Ultra GPU (80-core)

GeForce RTX 5090
VS
Apple M4 Ultra GPU (80-core)
Nvidia GeForce RTX 5090
GB202-300
Apple M4 Ultra GPU (80-core)
Custom

We performed a head-to-head comparison of the GeForce RTX 5090 32 GB with 170 pipelines and 21760 shaders against the 4 months newer Apple M4 Ultra GPU (80-core) that utilizes 1280 pipelines and 10240 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

  1. Review
  2. Differences
  3. Gaming performance
  4. Benchmarks
  5. AI
  6. Specs
  7. Comments (14)
Please note that the tests on the Apple M4 Ultra GPU (80-core) are done on an engineering sample provided by our insiders. The data will be more accurate after the final version of this GPU is available.

Key differences

Key distinctions and advantages of M4 Ultra GPU (80-core) over RTX 5090
Reasons to consider the GeForce RTX 5090
  • Performs significantly better (up to 2x) in 3DMark Steel Nomad Lite
  • 3.2x higher maximum theoretical performance (104.8 vs 32.3 TFLOPS)
  • Supports Nvidia DLSS 4 technology
  • Achieves 92% more points in the GeekBench 6 Compute test (419K vs 218K)
  • Has 2.1x more shading units (21760 vs 10240)
Reasons to consider the Apple M4 Ultra GPU (80-core)
  • Manufactured using a more efficient 3 nm process technology

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions
GPU
RTX 5090
vs
M4 Ultra GPU (80-core)

Games

FPS Table
Forza Horizon 5
336
247
233
187
 -
The Witcher 3
364
327
237
123
 -
Counter-Strike 2
363
265
202
99
 -
Far Cry 6
237
202
190
121
 -
Hogwarts Legacy
249
199
166
97
 -
CoD: Modern Warfare III
334
322
260
184
 -
Ghost of Tsushima
221
185
175
113
 -
Cyberpunk 2077
261
233
160
77
 -
Shadow of the Tomb Raider
329
302
238
128
 -
Average FPS by Resolution
1080p High 299 -
1080p Ultra 254 -
1440p Ultra 207 -
4K Ultra 125 -
Margin of Error Low High

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
RTX 5090 +103%
52764
M4 Ultra GPU (80-core)
25937
Time Spy 46873 -
Solar Bay 236689 -
Port Royal 38202 -
Fire Strike 87569 -
Wild Life Extreme 108751 -
Night Raid 206648 -
Sources: 3DMark [1]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
RTX 5090 +92%
419309
M4 Ultra GPU (80-core)
218394
Background Blur 333 img/sec -
Face Detection 298.5 img/sec -
Horizon Detection 21.7 Gpixels/sec -
Edge Detection 33.7 Gpixels/sec -
Gaussian Blur 34.5 Gpixels/sec -
Feature Matching 2.53 Gpixels/sec -
Stereo Matching 2850 Gpixels/sec -
Particle Physics 59146.9 FPS -
API OpenCL OpenCL
Sources: Geekbench [3]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
G2D Mark 1410 -
DirectX 11 340 FPS -
DirectX 12 179 FPS -
GPU Compute 24383 Ops/s -
Sources: PassMark [5] – 10759 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
Sources: Blender [9] – 3225 samples
Add your GPU benchmark result

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) 18948 -
Image Segmentation (HP) 55109 -
Image Super Resolution (Q) 58478 -
Face Detection (HP) 114685 -
Pose Estimation (Q) 344729 -
Text Classification (SP) 4464 -
Machine Translation (HP) 8184 -
Object Detection (SP) 27802 -
Depth Estimation (Q) 85572 -
Style Transfer (SP) 687080 -
Framework ONNX -
Backend DirectML -
Sources: Geekbench [9]

Specifications

Technical specifications of GeForce RTX 5090 and Apple M4 Ultra GPU (80-core)

General

Vendor Nvidia Apple
Build Discrete Integrated
Released January 7, 2025 May 1, 2025
Launch price (MSRP) $1999 -
Case Desktop Laptop
Purpose Gaming Professional
Segment High-end High-end
Architecture Blackwell 2.0 Apple M GPU
GPU Codename GB202-300 Custom
Rival Equivalent - - GeForce RTX 5080
Recommended CPU - Intel Core Ultra 9 285K or above - Apple M4 Ultra or above
Used in CPUs - - Apple M4 Ultra
Desktop GPU rating (#2nd place)

Graphics Processing Unit

Base Clock 2017 MHz 500 MHz
Boost Clock 2407 MHz 1578 MHz
Shading Units 21760 10240
Texture Mapping Units (TMUs) 680 640
Render Output Units (ROPs) 176 320
Compute Units (Pipelines) 170 1280
Tensor Cores 680 -
Ray-tracing Cores 170 -
L1 Cache 128KB per cluster -
L2 Cache 96MB shared -
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 424 GPixel/s 505 GPixel/s
Texture Fill Rate 1637 GTexel/s 1010 GTexel/s
FLOPS (FP32)
RTX 5090 +224%
104.8 TFLOPS
M4 Ultra GPU (80-core)
32.3 TFLOPS

Physical

Interface PCIe 5.0 x16 Custom
TGP 575 W 120 W
Manufacturing TSMC TSMC
Fabrication Process 4 nm 3 nm
Die Size 750 mm² -
Transistor Count 92.2 billion -
Transistor Density 122.93 MTr/mm² -

Memory

Memory Type GDDR7 System Shared
Memory Size 32 GB -
Memory Clock 1750 MHz 8533 MHz
Effective Memory Speed 28000 Mbps -
Bus 512-bit 1024-bit
ECC No No
Memory Bandwidth

API

DirectX 12.2 -
Vulkan 1.4 -
OpenGL 4.6 -
OpenCL 3.0 -
CUDA 12.0 -
Ray Tracing Yes Yes
DLSS DLSS 4 No
DisplayPort 2.1b -

Cast your vote

Choose between two graphics cards
395 (67.9%)
187 (32.1%)
Total votes: 582

Related comparisons

1. Apple M4 Ultra GPU (80-core) vs GeForce RTX 4070 Laptop
2. Apple M4 Ultra GPU (80-core) vs Apple M4 Max GPU (40-core)
3. Apple M4 Ultra GPU (80-core) vs Apple M2 Max GPU (38-core)
4. Apple M4 Ultra GPU (80-core) vs GeForce RTX 3080
5. Apple M4 Ultra GPU (80-core) vs Intel Arc 140V
6. GeForce RTX 5090 vs GeForce RTX 4090 (18)
7. GeForce RTX 5090 vs GeForce RTX 3090 (1)
8. GeForce RTX 5090 vs Apple M4 Max GPU (40-core) (2)
9. GeForce RTX 5090 vs GeForce RTX 5080 (4)
10. GeForce RTX 5090 vs GeForce RTX 5070 Ti

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
diddy February 1, 2026 at 07:37 AM
M4 ultra is an absolute trash gpu in most of the categories.
+2 Reply
Avatar
Name June 8, 2025 at 02:48 AM
Apple gpu is so ass.
+9 Reply
Avatar
A19 pro April 28, 2026 at 10:50 AM
A19 pro Gpu very good
0 Reply
Avatar
Azathoth13 March 8, 2025 at 02:18 AM
For those who makes animation or 3d stuff RTX 5090 is better choice is not multitasking it's about getting slow or lagging because of tflops it shows the amount of processing power that means rtx is way better than M4
+1 Reply
Avatar
Tuncay Aydin February 1, 2025 at 02:41 PM
Let's see TFLOPS per WATT M4 Ultra = 0.3075 (TFLOPS/Watt) RTX 5090 = 0.1824 (TFLOPS/Watt) The winner is M4 Ultra.
+24 Reply
Avatar
Nootdaddy February 13, 2025 at 10:26 AM
Who cares about watts lol
+14 Reply
Avatar
Somone February 15, 2025 at 10:13 PM
Nootdaddy, If you don't want your power connector to melt, I think you should care about it.
+9 Reply
Avatar
Azathoth13 March 8, 2025 at 02:21 AM
What's overall output you want get the job done faster / we are talking about amount of processing units and it already says apply can not take the market for people who don't want waste money, their M4 ultra maybe be good for photo editing but normally people care about tflops
+4 Reply
Avatar
Secret March 30, 2025 at 12:10 PM
Apple glazer final boss
+10 Reply
Avatar
Yikes October 27, 2025 at 11:35 PM
Triple the output at 35% reduced efficiency. I don't see how you think your math proves your point. 5090 wins. Time is money.
+3 Reply
Avatar
John January 22, 2025 at 07:22 AM
Who winner GeForce RTX 5090 vs Apple M4 Ultra
+34 Reply
Avatar
nerdlookingahh December 28, 2024 at 06:10 AM
Sure, but then RTX 5090 is like for gamers, and mac CAN run games, but it needs an emulator, and essentially, busniess owners wouldn't want some crazy power hungry PC, as the RTX 5090 in question here uses 600w while the M4 Ultra uses 120w so it has a better watt to teraflop ratio... and I'm not saying the RTX 5090 is bad, I'm just saying that they're both good, just at driffrent things.
+6 Reply
Avatar
ComputerNerd December 3, 2024 at 10:23 PM
Nvidia RTX 5090 has 109.7 TFLOPS. M4 Ultra has 36.9 TFLOPS. It is not even close. Nvidia RTX 5090 wins from a raw performance standpoint. Only issue is the price. Nvidia RTX 5090 starts at $1,600 for the GPU alone. For desktop users, this does not include the other parts. Examples: CPU that can keep up with the GPU, power supply, RAM, SSD, motherboard, case, cables, monitor, keyboard, and mouse.
+10 Reply
Avatar
Random comment February 13, 2025 at 05:11 PM
Am I the only one who thinks that a similar comparison is not really useful? Come on the m4 ultra will have a totally different community that will buy it (who needs more power for graphics and video editing workloads) compared with an nvidia gpu (which are used for gaming the most of the time). Wouldn't a w7900 vs m4 ultra make more sense than this?
+19 Reply
EnglishРусский