GeForce RTX 4090 vs RTX 4080
VS
Nvidia GeForce RTX 4090
AD102
Nvidia GeForce RTX 4080
AD103
We compared two discrete desktop gaming GPUs: the GeForce RTX 4090 24 GB with 128 pipelines and 16384 shaders against the RTX RTX 4080 16 GB that utilizes 76 pipelines and 9728 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
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 4090
- Performs significantly better (up to 40%) in 3DMark Steel Nomad Lite
- 70% higher maximum theoretical performance (82.6 vs 48.7 TFLOPS)
- Shows 20% higher average frame rate in modern games at QHD resolution – 177 vs 148 FPS
- Includes 8 GB more video memory
- Features 208 more tensor cores for effective ML and AI workloads
- Achieves 45% more points in the GeekBench 6 Compute test (316K vs 217K)
- Has 41% higher memory bandwidth: 1010 vs 716.8 GB/s
- Has 68% more shading units (16384 vs 9728)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 275 199 193 155 |
229 170 154 120 |
| The Witcher 3 | 292 268 191 101 |
245 210 157 81 |
| Counter-Strike 2 | 339 238 188 90 |
306 220 168 85 |
| Far Cry 6 | 203 179 170 104 |
181 163 143 88 |
| Hogwarts Legacy | 200 163 132 74 |
162 136 109 59 |
| CoD: Modern Warfare III | 266 263 219 151 |
217 213 167 111 |
| Ghost of Tsushima | 188 152 137 91 |
148 126 109 69 |
| Cyberpunk 2077 | 226 208 143 66 |
192 177 119 54 |
| Shadow of the Tomb Raider | 302 284 222 118 |
290 265 204 107 |
| 1080p High | 255 | 219 |
| 1080p Ultra | 217 | 187 |
| 1440p Ultra | 177 | 148 |
| 4K Ultra | 106 | 86 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 36299 | 28155 |
| Solar Bay | 187525 | 136995 |
| Port Royal | 26127 | 17984 |
| Fire Strike | 72432 | 64637 |
| Wild Life Extreme | 85218 | 59123 |
| Night Raid | 195813 | 185072 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 318.9 img/sec | 250.4 img/sec |
| Face Detection | 222.8 img/sec | 190 img/sec |
| Horizon Detection | 14.2 Gpixels/sec | 9.56 Gpixels/sec |
| Edge Detection | 21 Gpixels/sec | 12.8 Gpixels/sec |
| Gaussian Blur | 23.9 Gpixels/sec | 15.3 Gpixels/sec |
| Feature Matching | 2.38 Gpixels/sec | 1.97 Gpixels/sec |
| Stereo Matching | 1950 Gpixels/sec | 1130 Gpixels/sec |
| Particle Physics | 48090.4 FPS | 28795.5 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1303 | 1251 |
| DirectX 11 | 323 FPS | 313 FPS |
| DirectX 12 | 151 FPS | 133 FPS |
| GPU Compute | 25991 Ops/s | 20303 Ops/s |
Blender
Blender GPU
Recent User Tests
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 |
GeForce RTX 4080
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-05-02 (Rennsport) | Geekbench 6 OpenCL | 267332 |
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) | 15600 | 13466 |
| Image Segmentation (HP) | 36657 | 34767 |
| Image Super Resolution (Q) | 48114 | 42687 |
| Face Detection (HP) | 78111 | 70927 |
| Pose Estimation (Q) | 289639 | 239350 |
| Text Classification (SP) | 4074 | 3606 |
| Machine Translation (HP) | 6349 | 6519 |
| Object Detection (SP) | 21186 | 18153 |
| Depth Estimation (Q) | 75599 | 65667 |
| Style Transfer (SP) | 601428 | 414848 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 4090 and RTX 4080General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | September 20, 2022 | September 20, 2022 |
| Launch price (MSRP) | $1599 | $1199 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ada Lovelace | Ada Lovelace |
| GPU Codename | AD102 | AD103 |
| Rival Equivalent | - | - Radeon RX 7900 XTX |
| Successor | - GeForce RTX 5090 | - GeForce RTX 5080 |
| Recommended CPU | - Intel Core i9 14900K or above | - Intel Core i7 14700K or above |
Desktop GPU rating (3rd and 10th place)
Graphics Processing Unit
| Base Clock | 2235 MHz | 2205 MHz |
| Boost Clock | 2520 MHz | 2505 MHz |
| Shading Units | 16384 | 9728 |
| Texture Mapping Units (TMUs) | 512 | 304 |
| Render Output Units (ROPs) | 176 | 112 |
| Compute Units (Pipelines) | 128 | 76 |
| Tensor Cores | 512 | 304 |
| Ray-tracing Cores | 128 | 76 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 72MB shared | 64MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 444 GPixel/s | 281 GPixel/s |
| Texture Fill Rate | 1290 GTexel/s | 762 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 450 W | 320 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 5 nm |
| Die Size | 609 mm² | 379 mm² |
| Transistor Count | 76.3 billion | 45 billion |
| Transistor Density | 125.29 MTr/mm² | 118.73 MTr/mm² |
Memory
| Memory Type | GDDR6X | GDDR6X |
| Memory Size | 24 GB | 16 GB |
| Memory Clock | 2625 MHz | 1400 MHz |
| Effective Memory Speed | 21000 Mbps | 22400 Mbps |
| Bus | 384-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 8.9 | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | DLSS 3 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 45