Nvidia RTX 4000 Ada vs GeForce RTX 4090
VS
Nvidia RTX 4000 Ada
AD104
Nvidia GeForce RTX 4090
AD102
We compared two discrete desktop gaming GPUs: the Nvidia RTX 4000 Ada 20 GB with 48 pipelines and 6144 shaders against the 11 months older GeForce RTX 4090 24 GB 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
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 4090
- Performs significantly better (up to 2.9x) in 3DMark Steel Nomad Lite
- 3.1x higher maximum theoretical performance (82.6 vs 26.7 TFLOPS)
- Shows 92% higher average frame rate in modern games at QHD resolution – 177 vs 92 FPS
- Includes 4 GB more video memory
- Has 2.8x higher memory bandwidth: 1010 vs 360 GB/s
- Features 320 more tensor cores for effective ML and AI workloads
- Achieves 2.1x more points in the GeekBench 6 Compute test (316K vs 151K)
- Has 2.7x more shading units (16384 vs 6144)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 149 98 91 63 |
275 199 193 155 |
| The Witcher 3 | 177 143 103 54 |
292 268 191 101 |
| Counter-Strike 2 | 253 201 135 80 |
339 238 188 90 |
| Far Cry 6 | 131 123 101 58 |
203 179 170 104 |
| Hogwarts Legacy | 102 82 66 34 |
200 163 132 74 |
| CoD: Modern Warfare III | 126 119 88 56 |
266 263 219 151 |
| Ghost of Tsushima | 94 79 61 33 |
188 152 137 91 |
| Cyberpunk 2077 | 112 96 64 30 |
226 208 143 66 |
| Shadow of the Tomb Raider | 175 157 119 65 |
302 284 222 118 |
| 1080p High | 147 | 255 |
| 1080p Ultra | 122 | 217 |
| 1440p Ultra | 92 | 177 |
| 4K Ultra | 53 | 106 |
| Margin of Error | High | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 14438 | 36299 |
| Solar Bay | 65875 | 187525 |
| Port Royal | 8974 | 26127 |
| Fire Strike | 37396 | 72432 |
| Wild Life Extreme | - | 85218 |
| Night Raid | 158480 | 195813 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 235.3 img/sec | 318.9 img/sec |
| Face Detection | 157.9 img/sec | 222.8 img/sec |
| Horizon Detection | 5.53 Gpixels/sec | 14.2 Gpixels/sec |
| Edge Detection | 7.44 Gpixels/sec | 21 Gpixels/sec |
| Gaussian Blur | 7.87 Gpixels/sec | 23.9 Gpixels/sec |
| Feature Matching | 1.58 Gpixels/sec | 2.38 Gpixels/sec |
| Stereo Matching | 737.7 Gpixels/sec | 1950 Gpixels/sec |
| Particle Physics | 22409.2 FPS | 48090.4 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1110 | 1303 |
| DirectX 11 | 203 FPS | 323 FPS |
| DirectX 12 | 93 FPS | 151 FPS |
| GPU Compute | 11869 Ops/s | 25991 Ops/s |
Blender
Blender GPU
Recent User Tests
Nvidia RTX 4000 Ada
No benchmark results yet
GeForce RTX 4090
| Date | Benchmark | Result |
|---|---|---|
| 📘 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) | 9717 | 15600 |
| Image Segmentation (HP) | 19365 | 36657 |
| Image Super Resolution (Q) | 29227 | 48114 |
| Face Detection (HP) | 40416 | 78111 |
| Pose Estimation (Q) | 105639 | 289639 |
| Text Classification (SP) | 3577 | 4074 |
| Machine Translation (HP) | 4193 | 6349 |
| Object Detection (SP) | 10820 | 21186 |
| Depth Estimation (Q) | 36574 | 75599 |
| Style Transfer (SP) | 200936 | 601428 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Nvidia RTX 4000 Ada and GeForce RTX 4090General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | August 9, 2023 | September 20, 2022 |
| Launch price (MSRP) | $1250 | $1599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ada Lovelace | Ada Lovelace |
| GPU Codename | AD104 | AD102 |
| Successor | - | - GeForce RTX 5090 |
| Recommended CPU | - Intel Core i7 14700K or above | - Intel Core i9 14900K or above |
Desktop GPU rating (35th and 3rd place)
Graphics Processing Unit
| Base Clock | 1500 MHz | 2235 MHz |
| Boost Clock | 2175 MHz | 2520 MHz |
| Shading Units | 6144 | 16384 |
| Texture Mapping Units (TMUs) | 192 | 512 |
| Render Output Units (ROPs) | 80 | 176 |
| Compute Units (Pipelines) | 48 | 128 |
| Tensor Cores | 192 | 512 |
| Ray-tracing Cores | 48 | 128 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 48MB shared | 72MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 174 GPixel/s | 444 GPixel/s |
| Texture Fill Rate | 418 GTexel/s | 1290 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 130 W | 450 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 5 nm |
| Die Size | 294 mm² | 609 mm² |
| Transistor Count | 35 billion | 76.3 billion |
| Transistor Density | 119.05 MTr/mm² | 125.29 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6X |
| Memory Size | 20 GB | 24 GB |
| Memory Clock | 2250 MHz | 2625 MHz |
| Effective Memory Speed | 18000 Mbps | 21000 Mbps |
| Bus | 160-bit | 384-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: 7