- Graphics Processor: GA104
- Cores: 4096
- TMUs / ROPs: 128 / 64
A entry-level Nvidia RTX A3000 Laptop graphics card with modest workstation performance (40/100). Suited for casual gaming and basic graphics tasks.
Review
Pros
- Hardware ray tracing support
- DLSS upscaling support
- Dedicated AI tensor cores
Cons
- Limited gaming performance at higher resolutions
- Older generation architecture
Compare Nvidia RTX A3000 Laptop with other products
Full Specifications
| 1080p High | 1080p Ultra | 1440p Ultra | 4K Ultra | |
|---|---|---|---|---|
| Forza Horizon 5 | 61 | — | — | — |
| The Witcher 3 | 90 | — | — | — |
| Counter-Strike 2 | 120 | — | — | — |
| Far Cry 6 | 76 | — | — | — |
| Hogwarts Legacy | 48 | — | — | — |
| Call of Duty | 63 | — | — | — |
| Ghost of Tsushima | 44 | — | — | — |
| Cyberpunk 2077 | 55 | — | — | — |
| Tomb Raider | 91 | — | — | — |
| Average FPS | 72 | — | — | — |
Multiplatform graphics benchmark suite that directly correlates with performance in modern games
| Steel Nomad Lite Score | 8151 |
|---|---|
| Time Spy | 7594 |
| Solar Bay | 33550 |
| Port Royal | 4542 |
| Fire Strike | 19850 |
| Wild Life Extreme | 3521 |
| Night Raid | 75780 |
GPU test for computational tasks (image processing, photography, computer vision, and ML)
| GB6 Compute Score | 89769 |
|---|---|
| Background Blur | 140.7 img/sec |
| Face Detection | 73 img/sec |
| Horizon Detection | 4.08 Gpixels/sec |
| Edge Detection | 5.52 Gpixels/sec |
| Gaussian Blur | 4.3 Gpixels/sec |
| Feature Matching | 0.9 Gpixels/sec |
| Stereo Matching | 414.8 Gpixels/sec |
| Particle Physics | 12769.8 FPS |
| API | OpenCL |
Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
Rendering performance test for 3D modeling
Tests throughput of AI operations in single, half, and quantized precision
| GB6 ML Single Precision | 12265 |
|---|---|
| GB6 ML Half Precision | 20980 |
| GB6 ML Quantized | 8142 |
| Image Classification (SP) | 4552 |
| Image Segmentation (HP) | 11804 |
| Image Super Resolution (Q) | 11986 |
| Face Detection (HP) | 21457 |
| Pose Estimation (Q) | 52678 |
| Text Classification (SP) | 2248 |
| Machine Translation (HP) | 2727 |
| Object Detection (SP) | 6308 |
| Depth Estimation (Q) | 20307 |
| Style Transfer (SP) | 111653 |
| Framework | ONNX |
| Backend | DirectML |
| Vendor | Nvidia |
|---|---|
| Build | Discrete |
| Released | 12-Apr-21 |
| Case | Laptop |
| Purpose | Professional |
| Segment | Mid-range |
| Architecture | Ampere |
| GPU Codename | GA104 |
| Recommended CPU | -Intel Core i7 12800HXor above |
| Base Clock | 600-1080 MHz (configurable) |
|---|---|
| Boost Clock | 1180-1560 MHz (configurable) |
| Shading Units | 4096 |
| Texture Mapping Units (TMUs) | 128 |
| Render Output Units (ROPs) | 64 |
| Compute Units (Pipelines) | 32 |
| Tensor Cores | 128 |
| Ray-tracing Cores | 32 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 4MB shared |
| Instructions Per Cycle | 2 IPC |
| Pixel Fill Rate | 76-100 GPixel/s |
|---|---|
| Texture Fill Rate | 151-200 GTexel/s |
| FLOPS (FP32) | 9.7-12.8 TFLOPS |
| Interface | PCIe 4.0 x16 |
|---|---|
| TGP | 60-130 W (configurable) |
| Manufacturing | Samsung |
| Fabrication Process | 8 nm |
| Die Size | 392 mm² |
| Transistor Count | 17.4 billion |
| Transistor Density | 44.39 MTr/mm² |
| Max. Temperature | — |
| Memory Type | GDDR6 |
|---|
| DirectX | 12 |
|---|---|
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 8.6 |
| Ray Tracing | Yes |
| DLSS | DLSS 2 |
| DisplayPort | 1.4a |
