AMD Radeon 890M vs GeForce RTX 4060 Laptop

We performed a head-to-head comparison of the Radeon 890M with 16 pipelines and 1024 shaders against the 1 year and 4 months older GeForce RTX 4060 Mobile 8 GB that utilizes 24 pipelines and 3072 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 -

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 RTX 4060 Mobile over Radeon 890M
Reasons to consider the Radeon 890M
  • Manufactured using a more efficient 4 nm process technology
Reasons to consider the GeForce RTX 4060 Laptop
  • Performs significantly better (up to 3.2x) in 3DMark Steel Nomad Lite
  • Shows 3.5x higher average frame rate in modern games at QHD resolution – 67 vs 19 FPS
  • 2.5x higher maximum theoretical performance (14.6 vs 5.9 TFLOPS)
  • Includes 8 GB of dedicated GDDR6 memory
  • Supports Nvidia DLSS 3 technology
  • Achieves 2.3x more points in the GeekBench 6 Compute test (97K vs 42K)
  • Has 3x more shading units (3072 vs 1024)
  • Features 96 tensor cores for effective deep learning and AI workloads

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5
57
30
25
14
120
77
66
44
The Witcher 3
36
32
18
-
141
112
79
42
Counter-Strike 2
51
34
25
10
205
153
110
54
Far Cry 6
43
37
23
13
103
92
75
43
Hogwarts Legacy
25
17
14
-
74
62
45
25
CoD: Modern Warfare III
39
34
22
14
95
85
59
37
Ghost of Tsushima
25
17
12
-
74
60
42
23
Cyberpunk 2077
23
23
12
-
82
72
42
21
Shadow of the Tomb Raider
43
34
21
10
127
116
83
43
Average FPS by Resolution
1080p High 38 113
1080p Ultra 29 92
1440p Ultra 19 67
4K Ultra 10 37
Margin of Error Low Low

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
10212
Time Spy 3305 10397
Solar Bay 15412 45002
Port Royal 1795 5819
Fire Strike 8908 26481
Wild Life Extreme 6884 19820
Night Raid 37640 98330
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
42932
97986
Background Blur 98.6 img/sec 142.7 img/sec
Face Detection 42 img/sec 103.7 img/sec
Horizon Detection 1.25 Gpixels/sec 3.83 Gpixels/sec
Edge Detection 1.6 Gpixels/sec 4.93 Gpixels/sec
Gaussian Blur 1.69 Gpixels/sec 4.63 Gpixels/sec
Feature Matching 0.55 Gpixels/sec 1.27 Gpixels/sec
Stereo Matching 214.8 Gpixels/sec 430.4 Gpixels/sec
Particle Physics 7757.7 FPS 13519.5 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

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
17346
G2D Mark 979 731
DirectX 11 73 FPS 155 FPS
DirectX 12 37 FPS 72 FPS
GPU Compute 4162 Ops/s 6789 Ops/s
Sources: PassMark [5], [6] – 2175 & 22366 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
302.04
3293.54
Sources: Blender [9], [10] – 94 & 4321 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Radeon 890M
No benchmark results yet
GeForce RTX 4060 Laptop
DateBenchmarkResult
📘 2026-09-04 (Viru)Geekbench 6 OpenCL115610
📘 2026-09-04 (Viru)Cinebench 202410216
📘 2026-02-21 (Бенкдикт)Geekbench 6 OpenCL101184
📘 2025-12-18 (AmirtheX)Geekbench 6 OpenCL107583
📘 2025-11-17 (kritan)Cinebench 202410306

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
17683
GB6 ML Half Precision
15157
30738
GB6 ML Quantized
13612
Image Classification (SP) 3563 7421
Image Segmentation (HP) 6170 19041
Image Super Resolution (Q) 10762 20913
Face Detection (HP) 13773 35464
Pose Estimation (Q) 37861 67110
Text Classification (SP) 2572 3086
Machine Translation (HP) 4699 4740
Object Detection (SP) 2845 8644
Depth Estimation (Q) 17260 32456
Style Transfer (SP) 86751 142039
Framework ONNX ONNX
Backend DirectML DirectML
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Radeon 890M and GeForce RTX 4060 Laptop

General

Vendor Amd Nvidia
Build Integrated Discrete
Released June 3, 2024 February 22, 2023
Case Laptop Laptop
Purpose Generic Gaming
Segment Mid-range Mid-range
Architecture RDNA 3.5 Ada Lovelace
GPU Codename Strix Point AD107 (GN21-X4)
Rival Equivalent - Intel Arc 140V -
Successor - Radeon 8060S - GeForce RTX 5060 Laptop
Recommended CPU - AMD Ryzen AI 9 HX 370 or above - Intel Core Ultra 7 155H or above
Used in CPUs - AMD Ryzen AI 9 HX 470
- AMD Ryzen AI 9 HX 475
- AMD Ryzen Z2 Extreme
- AMD Ryzen AI 9 HX 375
- AMD Ryzen AI 9 HX 370
-
Laptop GPU ranking (80th and 43rd place)

Graphics Processing Unit

Base Clock 400 MHz 1140-2295 MHz (configurable)
Boost Clock 2900 MHz 1470-2370 MHz (configurable)
Shading Units 1024 3072
Texture Mapping Units (TMUs) 64 96
Render Output Units (ROPs) 32 48
Compute Units (Pipelines) 16 24
Tensor Cores No 96
Ray-tracing Cores 16 24
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 2MB shared 32MB shared
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 93 GPixel/s 71-114 GPixel/s
Texture Fill Rate 186 GTexel/s 141-228 GTexel/s
FLOPS (FP32)
5.9 TFLOPS
9-14.6 TFLOPS

Physical

Interface PCIe 4.0 x8 PCIe 4.0 x16
TGP 15 W 35-140 W (configurable)
Manufacturing TSMC TSMC
Fabrication Process 4 nm 5 nm
Die Size 233 mm² 156 mm²
Transistor Count 34 billion 18.9 billion
Transistor Density 145.92 MTr/mm² 121.15 MTr/mm²
Max. Temperature 100°C -

Memory

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

API

DirectX 12 12
Vulkan 1.4 1.3
OpenGL 4.6 4.6
OpenCL 2.1 3.0
CUDA None 8.9
Ray Tracing Yes Yes
DLSS No DLSS 3
DisplayPort 2.1 1.4a

Cast your vote

Choose between two graphics cards
51 (48.6%)
54 (51.4%)
Total votes: 105

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
WoodlandITguy November 29, 2024 at 03:34 PM
The 890M when paired with the correct RAM (at least 32GB of LPDDR5x at 7500mhz) and run at 54W (the Ryzen AI 9 HX 370 can be configured to run at 54W) should be able to blow these test bench numbers out of the water. There are a few mini-PCs out there that do run the Radeon 890M WAY higher than the benchmarks shown here. Why laptop manufacturers don't configure these chips to run at 54W is confusing and seems to bias the Nvidia GPUs. I deploy PCs as part of my job, I haven't had the chance to test the 890M in a PC or laptop yet, but I have extensively tested the Radeon 780M in dozens of machines and I get better numbers than what is show here for the 890M which is odd. That tells me these tests weren't conducted correctly. the 780M has 12 graphics cores clocked at 2700mhz where as the 890M has 16 graphics cores clocked at 2900mhz. It stands to reason that since the 890M has 4 more cores clocked at a higher clockspeed, it should handily outperform the older 780M.
+15 Reply
Avatar
David March 18, 2026 at 09:37 AM
so...the high buss ram is the more performance you can get on these APU...
+1 Reply