AMD Radeon 890M vs GeForce RTX 3060
VS
AMD Radeon 890M
Strix Point
Nvidia GeForce RTX 3060
GA106
We performed a head-to-head comparison of the Radeon 890M with 16 pipelines and 1024 shaders against the 3 years and 5 months older GeForce RTX 3060 12 GB that utilizes 28 pipelines and 3584 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
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
DeviceFacts Final Score
Overall video card score
The "Energy Efficiency" metric has less impact on the DeviceFacts Score for desktop GPU.
Key differences
Reasons to consider the Radeon 890M
- Manufactured using a more efficient 4 nm process technology
Reasons to consider the GeForce RTX 3060
- Performs significantly better (up to 2.8x) in 3DMark Steel Nomad Lite
- Shows 3.2x higher average frame rate in modern games at QHD resolution – 60 vs 19 FPS
- Includes 12 GB of dedicated GDDR6 memory
- 2.2x higher maximum theoretical performance (12.7 vs 5.9 TFLOPS)
- Achieves 2.1x more points in the GeekBench 6 Compute test (91K vs 42K)
- Supports Nvidia DLSS 2 technology
- Has 3.5x more shading units (3584 vs 1024)
- Features 112 tensor cores for effective deep learning and AI workloads
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 57 30 25 14 |
112 68 60 39 |
| The Witcher 3 | 36 32 18 - |
122 100 74 39 |
| Counter-Strike 2 | 51 34 25 10 |
181 137 99 48 |
| Far Cry 6 | 43 37 23 13 |
95 85 67 37 |
| Hogwarts Legacy | 25 17 14 - |
65 57 40 18 |
| CoD: Modern Warfare III | 39 34 22 14 |
80 74 53 31 |
| Ghost of Tsushima | 25 17 12 - |
62 50 37 20 |
| Cyberpunk 2077 | 23 23 12 - |
68 64 38 16 |
| Shadow of the Tomb Raider | 43 34 21 10 |
109 98 70 36 |
| 1080p High | 38 | 99 |
| 1080p Ultra | 29 | 81 |
| 1440p Ultra | 19 | 60 |
| 4K Ultra | 10 | 32 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 3305 | 8754 |
| Solar Bay | 15412 | 41158 |
| Port Royal | 1795 | 5145 |
| Fire Strike | 8908 | 22304 |
| Wild Life Extreme | 6884 | 17728 |
| Night Raid | 37640 | 97159 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 98.6 img/sec | 149.6 img/sec |
| Face Detection | 42 img/sec | 91 img/sec |
| Horizon Detection | 1.25 Gpixels/sec | 4.07 Gpixels/sec |
| Edge Detection | 1.6 Gpixels/sec | 5.58 Gpixels/sec |
| Gaussian Blur | 1.69 Gpixels/sec | 3.92 Gpixels/sec |
| Feature Matching | 0.55 Gpixels/sec | 1.01 Gpixels/sec |
| Stereo Matching | 214.8 Gpixels/sec | 372.9 Gpixels/sec |
| Particle Physics | 7757.7 FPS | 12226.3 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 979 | 965 |
| DirectX 11 | 73 FPS | 127 FPS |
| DirectX 12 | 37 FPS | 68 FPS |
| GPU Compute | 4162 Ops/s | 8231 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon 890M
No benchmark results yet
GeForce RTX 3060
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-07 (tach) | Cinebench 2024 | 7952 |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 3563 | 6645 |
| Image Segmentation (HP) | 6170 | 15338 |
| Image Super Resolution (Q) | 10762 | 14283 |
| Face Detection (HP) | 13773 | 28862 |
| Pose Estimation (Q) | 37861 | 61313 |
| Text Classification (SP) | 2572 | 2463 |
| Machine Translation (HP) | 4699 | 3793 |
| Object Detection (SP) | 2845 | 7712 |
| Depth Estimation (Q) | 17260 | 25461 |
| Style Transfer (SP) | 86751 | 123233 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon 890M and GeForce RTX 3060General
| Vendor | Amd | Nvidia |
| Build | Integrated | Discrete |
| Released | June 3, 2024 | January 12, 2021 |
| Launch price (MSRP) | - | $329 |
| Case | Laptop | Desktop |
| Purpose | Generic | Gaming |
| Segment | Mid-range | Mid-range |
| Architecture | RDNA 3.5 | Ampere |
| GPU Codename | Strix Point | GA106 |
| Rival Equivalent | - Intel Arc 140V | - Radeon RX 6700 XT |
| Successor | - Radeon 8060S | - GeForce RTX 5060 |
| Recommended CPU | - AMD Ryzen AI 9 HX 370 or above | - Intel Core i5 12600K 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 place)
Desktop GPU rating (#58th place)
Graphics Processing Unit
| Base Clock | 400 MHz | 1320 MHz |
| Boost Clock | 2900 MHz | 1777 MHz |
| Shading Units | 1024 | 3584 |
| Texture Mapping Units (TMUs) | 64 | 112 |
| Render Output Units (ROPs) | 32 | 48 |
| Compute Units (Pipelines) | 16 | 28 |
| Tensor Cores | No | 112 |
| Ray-tracing Cores | 16 | 28 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 2MB shared | 3MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 93 GPixel/s | 85 GPixel/s |
| Texture Fill Rate | 186 GTexel/s | 199 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | PCIe 4.0 x16 |
| TGP | 15 W | 170 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 4 nm | 8 nm |
| Die Size | 233 mm² | 276 mm² |
| Transistor Count | 34 billion | 12 billion |
| Transistor Density | 145.92 MTr/mm² | 43.48 MTr/mm² |
| Max. Temperature | 100°C | - |
Memory
| Memory Type | System Shared | GDDR6 |
| Memory Size | - | 12 GB |
| Memory Clock | - | 1875 MHz |
| Effective Memory Speed | - | 15000 Mbps |
| Bus | - | 192-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 | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 2 |
| DisplayPort | 2.1 | 1.4a |
Cast your vote
Total votes: 9