- Graphics Processor: AD107
- Cores: 2816
- TMUs / ROPs: 88 / 48
Expert Verdict
A entry-level Nvidia RTX 2000 Ada graphics card with modest gaming performance (40/100). Suited for casual gaming and basic graphics tasks.
Review
Gaming
40
Workstation
40
AI/ML
31
Energy Efficiency
74
Quick Comparison Final Score
39
Pros
- Large 16GB memory pool
- Hardware ray tracing support
- DLSS upscaling support
- Dedicated AI tensor cores
Cons
- No significant drawbacks for its tier
Compare Nvidia RTX 2000 Ada with other products
Full Specifications
Games
Performance
Forza Horizon 5
The Witcher 3
Counter-Strike 2
Far Cry 6
Hogwarts Legacy
Call of Duty
Ghost of Tsushima
Cyberpunk 2077
Tomb Raider
Average FPS
1080p High
1080p Ultra
1440p Ultra
4K Ultra
FPS Table
| 1080p High | 1080p Ultra | 1440p Ultra | 4K Ultra | |
|---|---|---|---|---|
| Forza Horizon 5 | — | — | — | — |
| The Witcher 3 | — | — | — | — |
| Counter-Strike 2 | — | — | — | — |
| Far Cry 6 | — | — | — | — |
| Hogwarts Legacy | — | — | — | — |
| Call of Duty | — | — | — | — |
| Ghost of Tsushima | — | — | — | — |
| Cyberpunk 2077 | — | — | — | — |
| Tomb Raider | — | — | — | — |
| Average FPS | — | — | — | — |
Average FPS by Resolution
1080p High
—
1080p Ultra
—
1440p Ultra
—
4K Ultra
—
Margin of Error
—
3D Mark
Multiplatform graphics benchmark suite that directly correlates with performance in modern games
| Steel Nomad Lite Score | — |
|---|---|
| Time Spy | — |
| Solar Bay | — |
| Port Royal | — |
| Fire Strike | — |
| Wild Life Extreme | — |
| Night Raid | — |
GeekBench 6 OpenCL
GPU test for computational tasks (image processing, photography, computer vision, and ML)
| GB6 Compute Score | 89677 |
|---|---|
| Background Blur | 170.5 img/sec |
| Face Detection | 102.8 img/sec |
| Horizon Detection | 3.25 Gpixels/sec |
| Edge Detection | 4.12 Gpixels/sec |
| Gaussian Blur | 4.06 Gpixels/sec |
| Feature Matching | 1.13 Gpixels/sec |
| Stereo Matching | 353.4 Gpixels/sec |
| Particle Physics | 12273.1 FPS |
| API | OpenCL |
Passmark Graphics
Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
Blender
Rendering performance test for 3D modeling
GeekBench 6 ML
Tests throughput of AI operations in single, half, and quantized precision
| GB6 ML Single Precision | 15501 |
|---|---|
| GB6 ML Half Precision | 27554 |
| GB6 ML Quantized | 12117 |
| Image Classification (SP) | 6382 |
| Image Segmentation (HP) | 16489 |
| Image Super Resolution (Q) | 17694 |
| Face Detection (HP) | 32453 |
| Pose Estimation (Q) | 56937 |
| Text Classification (SP) | 3097 |
| Machine Translation (HP) | 4324 |
| Object Detection (SP) | 7656 |
| Depth Estimation (Q) | 29700 |
| Style Transfer (SP) | 116441 |
| Framework | ONNX |
| Backend | DirectML |
General
| Vendor | Nvidia |
|---|---|
| Build | Discrete |
| Released | 12-Feb-22 |
| Case | Desktop |
| Purpose | Professional |
| Segment | Mid-range |
| Architecture | Ada Lovelace |
| GPU Codename | AD107 |
| Recommended CPU | -Intel Core i7 14700Kor above |
Graphics Processing Unit
| Base Clock | 1620 MHz |
|---|---|
| Boost Clock | 2130 MHz |
| Shading Units | 2816 |
| Texture Mapping Units (TMUs) | 88 |
| Render Output Units (ROPs) | 48 |
| Compute Units (Pipelines) | 22 |
| Tensor Cores | 88 |
| Ray-tracing Cores | 22 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 12MB shared |
| Instructions Per Cycle | 2 IPC |
Raw Performance
| Pixel Fill Rate | 102 GPixel/s |
|---|---|
| Texture Fill Rate | 187 GTexel/s |
| FLOPS (FP32) | 12 TFLOPS |
Physical
| Interface | PCIe 4.0 x8 |
|---|---|
| TGP | 70 W |
| Manufacturing | TSMC |
| Fabrication Process | 5 nm |
| Die Size | 159 mm² |
| Transistor Count | 18 billion |
| Transistor Density | 113.21 MTr/mm² |
| Max. Temperature | — |
Memory
| Memory Type | GDDR6 |
|---|
API
| DirectX | 12 |
|---|---|
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 8.9 |
| Ray Tracing | Yes |
| DLSS | DLSS 3 |
| DisplayPort | 1.4a |
