3DMark Benchmark (DirectX, Raytracing)
3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value.

The GIGABYTE Radeon Pro W7900 has 6144 shader units and these clock a maximum of 2.50 GHz which results in an FP32 computing power of 61.32 TFLOPS.

The ASUS ROG Strix GeForce RTX 4090 has 16384 shader units and these clock at a maximum of 2.55 GHz and achieve an FP32 computing power of 83.56 TFLOPS.
In FP32 performance, the ASUS ROG Strix GeForce RTX 4090 is 36 % faster than the GIGABYTE Radeon Pro W7900.
| GPU | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Based on | AMD Radeon Pro W7900 | NVIDIA GeForce RTX 4090 |
| GPU Chip | Navi 31 | AD102-300-A1 |
| Streaming Multiprocessors | 96 | 128 |
| Shader | 6144 | 16384 |
| Render Output Units | 192 | 176 |
| Texture Units | 384 | 512 |
| Raytracing Cores | 96 | 128 |
| Memory | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Memory Size | 48 GB | 24 GB |
| Memory Type | GDDR6 | GDDR6X |
| Memory Clock | 2.250 GHz | 1.313 GHz |
| Memory Speed | 18.0 Gbps | 21.0 Gbps |
| Memory bandwidth | 864 GB/s | 1,008 GB/s |
| Memory Interface | 384 bit | 384 bit |
| Clock Speeds | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Base Clock | 1.855 GHz | 2.235 GHz |
| Boost Clock | 2.495 GHz | 2.550 GHz |
| Overclocking | Yes | Yes |
| Thermal Design | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| TDP | 295 W | 450 W |
| Tjunction max | 99 °C | 90 °C |
| PCIe-Power | 2 x 8-Pin | 1 x 16-Pin |
| Cooler & Fans | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Fan-Type | Radial | Axial |
| Fan 1 | 1 x 75 mm | 3 x 110 mm |
| Cooler-Type | Air cooling | Air cooling |
| Noise (Idle) | 0 dB | 0 dB |
| Connectivity | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Max. Displays | 4 | 4 |
| HDCP | 2.3 | 2.3 |
| HDMI | -- | 2x HDMI 2.1a |
| DisplayPort | 4x DP 2.1 | 3x DP 1.4a |
| Featureset | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Max. resolution | 7680x4320 | 7680x4320 |
| DirectX | 12_2 (Ultimate) | 12_2 (Ultimate) |
| Raytracing | Yes | Yes |
| DLSS / FSR | Yes | Yes |
| LED | No LED lighting | ASUS Aura Sync |
| Supported Video Codecs | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| h264 | Decode / Encode | Decode / Encode |
| h265 / HEVC | Decode / Encode | Decode / Encode |
| VP8 | Decode / Encode | Decode |
| VP9 | Decode / Encode | Decode |
| AV1 | Decode / Encode | Decode |
| Dimensions | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| Length | 293 mm | 358 mm |
| Height | 126 mm | 149 mm |
| Width | 42 mm | 70 mm |
| Width (Slots) | 2 Slots | 4 Slots |
| SFF-Ready | No | No |
| Additional data | GIGABYTE Radeon Pro W7900 | ASUS ROG Strix GeForce RTX 4090 |
|---|---|---|
| GPU Interface | PCIe 4.0 x 16 | PCIe 4.0 x 16 |
| Release date | Q2/2024 | Q4/2022 |
| Launch Price | 3,999 $ | 2,029 $ |
| Structure size | 5 nm | 5 nm |
| Part-no | W7900 AI TOP 48G | ROG-STRIX-RTX4090-24G-GAMING |
| Documents | data sheet | data sheet |
3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value.
Cyberpunk 2077 was developed by CD Projekt Red and is based on the development studio's own REDengine 4. Ray tracing is switched off in our benchmarks.
The Last of Us Part One is a game released by Sony in June 2013 exclusively for the Playstation and released for the PC in early 2023. The benchmark values here were determined at high details.
Battlefield 5 is a visually stunning game that is ideal as a graphics card benchmark. We test the game with maximum details on Windows 10.
Geekbench 6 is a cross-platform benchmark for main processors, which also carries out 3 different graphics benchmarks and outputs them in the form of a numerical value.
The theoretical computing power of the graphics card with single precision (32 bit) in TFLOPS indicates how many trillion FP32 floating point operations the graphics card (GPU) can perform per second.