GeForce RTX 4070 Laptop vs Apple M4 Ultra GPU (80-core)

We performed a head-to-head comparison of the GeForce RTX 4070 Mobile 8 GB with 36 pipelines and 4608 shaders against the 2 years and 3 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.

Some GPUs come in different configurations. For greater precision, pick a specific config below
TGP / Version
-
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 4070 Mobile
Reasons to consider the GeForce RTX 4070 Laptop
  • Includes 8 GB of dedicated GDDR6 memory
  • Supports Nvidia DLSS 3 technology
Reasons to consider the Apple M4 Ultra GPU (80-core)
  • Performs significantly better (up to 2x) in 3DMark Steel Nomad Lite
  • Manufactured using a more efficient 3 nm process technology
  • 61% higher maximum theoretical performance (32.3 vs 20 TFLOPS)
  • Achieves 90% more points in the GeekBench 6 Compute test (218K vs 115K)
  • Has 2.2x more shading units (10240 vs 4608)

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5
139
89
77
56
-
The Witcher 3
164
129
95
53
-
Counter-Strike 2
236
183
130
71
-
Far Cry 6
121
109
87
51
-
Hogwarts Legacy
91
77
60
28
-
CoD: Modern Warfare III
111
105
77
51
-
Ghost of Tsushima
85
69
53
29
-
Cyberpunk 2077
99
84
53
25
-
Shadow of the Tomb Raider
147
137
100
53
-
Average FPS by Resolution
1080p High 133 -
1080p Ultra 109 -
1440p Ultra 81 -
4K Ultra 46 -
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
Time Spy 12514 -
Solar Bay 54815 -
Port Royal 7416 -
Fire Strike 30057 -
Wild Life Extreme 23262 -
Night Raid 113672 -
Sources: 3DMark [1]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
Background Blur 158.5 img/sec -
Face Detection 116.5 img/sec -
Horizon Detection 4.35 Gpixels/sec -
Edge Detection 5.67 Gpixels/sec -
Gaussian Blur 6.44 Gpixels/sec -
Feature Matching 1.36 Gpixels/sec -
Stereo Matching 528.5 Gpixels/sec -
Particle Physics 16372.3 FPS -
API OpenCL OpenCL
Sources: Geekbench [3]

Cinebench 2024 GPU

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

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
G2D Mark 766 -
DirectX 11 177 FPS -
DirectX 12 85 FPS -
GPU Compute 8365 Ops/s -
Sources: PassMark [5] – 13217 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
Sources: Blender [9] – 2189 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
GeForce RTX 4070 Laptop
DateBenchmarkResult
📘 2026-06-05 (Wahid)Geekbench 6 OpenCL122515
📘 2026-06-05 (Wahid)Geekbench 6 OpenCL35869
Apple M4 Ultra GPU (80-core)
No benchmark results yet

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) 8642 -
Image Segmentation (HP) 20635 -
Image Super Resolution (Q) 26378 -
Face Detection (HP) 39776 -
Pose Estimation (Q) 105983 -
Text Classification (SP) 2995 -
Machine Translation (HP) 4507 -
Object Detection (SP) 10198 -
Depth Estimation (Q) 41078 -
Style Transfer (SP) 190315 -
Framework ONNX -
Backend DirectML -
Sources: Geekbench [9]

Specifications

Technical specifications of GeForce RTX 4070 Laptop and Apple M4 Ultra GPU (80-core)

General

Vendor Nvidia Apple
Build Discrete Integrated
Released February 22, 2023 May 1, 2025
Case Laptop Laptop
Purpose Gaming Professional
Segment High-end High-end
Architecture Ada Lovelace Apple M GPU
GPU Codename AD106 (GN21-X6) Custom
Rival Equivalent - - GeForce RTX 5080
Successor - GeForce RTX 5070 Laptop -
Recommended CPU - Intel Core Ultra 7 155H or above - Apple M4 Ultra or above
Used in CPUs - - Apple M4 Ultra
Laptop GPU ranking (#23rd place)

Graphics Processing Unit

Base Clock 735-2070 MHz (configurable) 500 MHz
Boost Clock 1230-2175 MHz (configurable) 1578 MHz
Shading Units 4608 10240
Texture Mapping Units (TMUs) 144 640
Render Output Units (ROPs) 48 320
Compute Units (Pipelines) 36 1280
Tensor Cores 144 -
Ray-tracing Cores 36 -
L1 Cache 128KB per cluster -
L2 Cache 32MB shared -
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 59-104 GPixel/s 505 GPixel/s
Texture Fill Rate 177-313 GTexel/s 1010 GTexel/s
FLOPS (FP32)
11.3-20 TFLOPS
32.3 TFLOPS

Physical

Interface PCIe 4.0 x16 Custom
TGP 35-140 W (configurable) 120 W
Manufacturing TSMC TSMC
Fabrication Process 5 nm 3 nm
Die Size 186 mm² -
Transistor Count 22.9 billion -
Transistor Density 123.12 MTr/mm² -

Memory

Memory Type GDDR6 System Shared
Memory Size 8 GB -
Memory Clock 2000 MHz 8533 MHz
Effective Memory Speed 16000 Mbps -
Bus 128-bit 1024-bit
ECC No No
Memory Bandwidth

API

DirectX 12 -
Vulkan 1.3 -
OpenGL 4.6 -
OpenCL 3.0 -
CUDA 8.9 -
Ray Tracing Yes Yes
DLSS DLSS 3 No
DisplayPort 1.4a -

Cast your vote

Choose between two graphics cards
13 (35.1%)
24 (64.9%)
Total votes: 37

User opinions

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