GeForce RTX 5090 Laptop vs RTX 4090
VS
Nvidia GeForce RTX 5090 Laptop
GB203-400
Nvidia GeForce RTX 4090
AD102
We performed a head-to-head comparison of the GeForce RTX 5090 Mobile with 82 pipelines and 10496 shaders against the 2 years and 3 months older RTX RTX 4090 that utilizes 128 pipelines and 16384 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 GeForce RTX 5090 Laptop
- Manufactured using a more efficient 4 nm process technology
- Supports Nvidia DLSS 4 technology
Reasons to consider the GeForce RTX 4090
- Performs significantly better (up to 61%) in 3DMark Steel Nomad Lite
- 82% higher maximum theoretical performance (82.6 vs 45.3 TFLOPS)
- Shows 30% higher average frame rate in modern games at QHD resolution – 177 vs 136 FPS
- Features 184 more tensor cores for effective ML and AI workloads
- Achieves 39% more points in the GeekBench 6 Compute test (316K vs 226K)
- Has 56% more shading units (16384 vs 10496)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 212 149 140 111 |
275 199 193 155 |
| The Witcher 3 | 225 201 143 75 |
292 268 191 101 |
| Counter-Strike 2 | 293 222 162 84 |
339 238 188 90 |
| Far Cry 6 | 167 153 134 83 |
203 179 170 104 |
| Hogwarts Legacy | 151 120 97 55 |
200 163 132 74 |
| CoD: Modern Warfare III | 196 190 149 101 |
266 263 219 151 |
| Ghost of Tsushima | 135 114 96 63 |
188 152 137 91 |
| Cyberpunk 2077 | 177 153 110 51 |
226 208 143 66 |
| Shadow of the Tomb Raider | 273 257 194 104 |
302 284 222 118 |
| 1080p High | 203 | 255 |
| 1080p Ultra | 173 | 217 |
| 1440p Ultra | 136 | 177 |
| 4K Ultra | 81 | 106 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 25015 | 36299 |
| Solar Bay | 115087 | 187525 |
| Port Royal | 16530 | 26127 |
| Fire Strike | 51145 | 72432 |
| Wild Life Extreme | 47290 | 85218 |
| Night Raid | 177560 | 195813 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 266.5 img/sec | 318.9 img/sec |
| Face Detection | 196.9 img/sec | 222.8 img/sec |
| Horizon Detection | 10.6 Gpixels/sec | 14.2 Gpixels/sec |
| Edge Detection | 15.2 Gpixels/sec | 21 Gpixels/sec |
| Gaussian Blur | 14.4 Gpixels/sec | 23.9 Gpixels/sec |
| Feature Matching | 1.89 Gpixels/sec | 2.38 Gpixels/sec |
| Stereo Matching | 1150 Gpixels/sec | 1950 Gpixels/sec |
| Particle Physics | 29783 FPS | 48090.4 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1108 | 1303 |
| DirectX 11 | 266 FPS | 323 FPS |
| DirectX 12 | 135 FPS | 151 FPS |
| GPU Compute | 11399 Ops/s | 25991 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 5090 Laptop
No benchmark results yet
GeForce RTX 4090
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-10-06 (Devansh) | Geekbench 6 OpenCL | 394674 |
| 📘 2026-10-06 (Devansh) | Geekbench 7 OpenCL | 338129 |
| 📘 2026-04-03 (afroman420IU) | Cinebench 2024 | 32578 |
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) | 12121 | 15600 |
| Image Segmentation (HP) | 33054 | 36657 |
| Image Super Resolution (Q) | 33652 | 48114 |
| Face Detection (HP) | 67213 | 78111 |
| Pose Estimation (Q) | 151395 | 289639 |
| Text Classification (SP) | 3209 | 4074 |
| Machine Translation (HP) | 6292 | 6349 |
| Object Detection (SP) | 15618 | 21186 |
| Depth Estimation (Q) | 57894 | 75599 |
| Style Transfer (SP) | 272117 | 601428 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 5090 Laptop and RTX 4090General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 6, 2025 | September 20, 2022 |
| Launch price (MSRP) | - | $1599 |
| Case | Laptop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Blackwell 2.0 | Ada Lovelace |
| GPU Codename | GB203-400 | AD102 |
| Successor | - | - GeForce RTX 5090 |
| Recommended CPU | - Intel Core Ultra 9 275HX or above | - Intel Core i9 14900K or above |
Laptop GPU ranking (#1st place)
Desktop GPU rating (#3rd place)
Graphics Processing Unit
| Base Clock | 990-1515 MHz (configurable) | 2235 MHz |
| Boost Clock | 1515-2160 MHz (configurable) | 2520 MHz |
| Shading Units | 10496 | 16384 |
| Texture Mapping Units (TMUs) | 328 | 512 |
| Render Output Units (ROPs) | 112 | 176 |
| Compute Units (Pipelines) | 82 | 128 |
| Tensor Cores | 328 | 512 |
| Ray-tracing Cores | 82 | 128 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 64MB shared | 72MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 170-242 GPixel/s | 444 GPixel/s |
| Texture Fill Rate | 497-708 GTexel/s | 1290 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| TGP | 95-175 W (configurable) | 450 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 5 nm |
| Die Size | 378 mm² | 609 mm² |
| Transistor Count | 45.6 billion | 76.3 billion |
| Transistor Density | 120.63 MTr/mm² | 125.29 MTr/mm² |
Memory
| Memory Type | GDDR7 | GDDR6X |
| Memory Size | 24 GB | 24 GB |
| Memory Clock | 1750 MHz | 2625 MHz |
| Effective Memory Speed | 28000 Mbps | 21000 Mbps |
| Bus | 256-bit | 384-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 10.1 | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | DLSS 3 |
| DisplayPort | 2.1a | 1.4a |
Cast your vote
Total votes: 39