Radeon 660M vs Radeon 610M

We compared two integrated laptop GPUs: the Radeon 660M with 6 pipelines and 384 shaders against the 9 months newer Radeon 610M that utilizes 2 pipelines and 128 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 Radeon 610M over Radeon 660M
Reasons to consider the Radeon 660M
  • Performs significantly better (up to 3x) in 3DMark Steel Nomad Lite
  • 2.5x higher maximum theoretical performance (1.5 vs 0.6 TFLOPS)
  • Achieves 2.8x more points in the GeekBench 6 Compute test (14K vs 5K)
  • Has 3x more shading units (384 vs 128)

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5
27
13
11
-
11
-
-
-
The Witcher 3
9
12
-
-
-
Counter-Strike 2
28
17
13
-
16
11
-
-
Far Cry 6
20
16
9
-
9
-
-
-
Hogwarts Legacy
10
-
-
-
-
CoD: Modern Warfare III
18
15
13
-
13
11
9
-
Ghost of Tsushima
13
-
-
-
-
-
-
-
Cyberpunk 2077
9
9
-
-
-
Shadow of the Tomb Raider
17
14
11
-
-
9
-
-
Average FPS by Resolution
1080p High 17 9
1080p Ultra 12 -
1440p Ultra 9 -
4K Ultra - -
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
Radeon 660M +201%
1341
Time Spy 1514 519
Solar Bay 6396 2068
Port Royal 586 291
Fire Strike 4879 1745
Wild Life Extreme 2676 998
Night Raid 18958 7335
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
Radeon 660M +176%
14065
Background Blur 36 img/sec 12 img/sec
Face Detection 16.4 img/sec 6.42 img/sec
Horizon Detection 0.48 Gpixels/sec 0.16 Gpixels/sec
Edge Detection 0.65 Gpixels/sec 0.23 Gpixels/sec
Gaussian Blur 0.53 Gpixels/sec 0.16 Gpixels/sec
Feature Matching 0.18 Gpixels/sec 0.07 Gpixels/sec
Stereo Matching 46.5 Gpixels/sec 18.2 Gpixels/sec
Particle Physics 2056.5 FPS 828.6 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
3044
G2D Mark 654 535
DirectX 11 47 FPS 17 FPS
DirectX 12 23 FPS 7 FPS
GPU Compute 1321 Ops/s 768 Ops/s
Sources: PassMark [5], [6] – 5 & 194 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
92.56
47.48
Sources: Blender [9], [10] – 4 & 47 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Radeon 660M
No benchmark results yet
Radeon 610M
DateBenchmarkResult
📘 2026-05-05 (StarSophia)Steel Nomad Light614

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
Radeon 660M +104%
3903
GB6 ML Half Precision
Radeon 660M +131%
4745
GB6 ML Quantized
2977
Image Classification (SP) 1465 660
Image Segmentation (HP) 1706 627
Image Super Resolution (Q) 4266 2053
Face Detection (HP) 5115 2153
Pose Estimation (Q) 12992 5787
Text Classification (SP) 1116 713
Machine Translation (HP) 1859 1114
Object Detection (SP) 1574 709
Depth Estimation (Q) 6538 3233
Style Transfer (SP) 26656 11091
Framework ONNX ONNX
Backend DirectML DirectML
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Radeon 660M and Radeon 610M

General

Vendor Amd Amd
Build Integrated Integrated
Released January 1, 2022 October 1, 2022
Case Laptop Laptop
Purpose Generic Generic
Segment Entry-level Entry-level
Architecture RDNA 2.0 RDNA 2.0
GPU Codename Rembrandt Mendocino
Successor - Radeon 8040S -
Recommended CPU - AMD Ryzen 5 6600H or above - AMD Ryzen 5 7520U or above
Used in CPUs - AMD Ryzen 5 150
- AMD Ryzen 5 7535U
- AMD Ryzen 5 7535HS
- AMD Ryzen 5 Pro 6650U
- AMD Ryzen 5 6600U
- AMD Ryzen 5 6600H
- AMD Ryzen 9 8945HX
- AMD Ryzen 9 8940HX
- AMD Ryzen 9 9850HX
- AMD Ryzen 9 9955HX
- AMD Ryzen 9 9955HX3D
- AMD Ryzen 5 9600X
- AMD Ryzen 7 9700X
- AMD Ryzen 9 7945HX3D
- and 6 more
Laptop GPU ranking (116th and 125th place)

Graphics Processing Unit

Base Clock 400 MHz 400 MHz
Boost Clock 1800-1900 MHz (configurable) 1900-2200 MHz (configurable)
Shading Units 384 128
Texture Mapping Units (TMUs) 24 8
Render Output Units (ROPs) 16 4
Compute Units (Pipelines) 6 2
Ray-tracing Cores 6 2
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 1024KB shared 2MB shared
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 29-30 GPixel/s 8-9 GPixel/s
Texture Fill Rate 43-46 GTexel/s 15-18 GTexel/s
FLOPS (FP32)
Radeon 660M +150%
1.4-1.5 TFLOPS
0.5-0.6 TFLOPS

Physical

Interface PCIe 4.0 x8 PCIe 4.0 x8
TGP 15 W 15 W
Manufacturing TSMC TSMC
Fabrication Process 6 nm 6 nm
Die Size 208 mm² 122 mm²
Transistor Count 13.1 billion 3.4 billion
Transistor Density 62.98 MTr/mm² 27.87 MTr/mm²

Memory

Memory Type System Shared System Shared
ECC No No

API

DirectX 12 12
Vulkan 1.2 1.3
OpenGL 4.6 4.6
OpenCL 2.0 2.0
Ray Tracing Yes Yes
DLSS No No

Cast your vote

Choose between two graphics cards
7 (87.5%)
1 (12.5%)
Total votes: 8

User opinions

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