The GPU (Graphics Processing Unit) or graphics card is the most important component in a workstation. This is because it’s the GPU that does most of the work when it comes to rendering graphics and video, running simulations and AI models. This guide will teach you everything you need to know so you pick the perfect model for your workstation.
AMD workstation GPUs feature a whole host of extra features and capabilities that their consumer counterparts lack.
Certified Drivers ISVs such as Autodesk, Dassault and Siemens certify their applications, ensuring optimal stability backed by enterprise-class customer support.
Enterprise-class components ensure better reliability and resiliency, reducing failure rates especially when used at full load for longer periods of time.
Error correcting code (ECC) memory acts to protect data from corruption, so any errors are eradicated prior to them affecting the workload being processed.
Larger onboard frame buffers than consumer GPUs enable larger and more complex renders and compute simulations to be processed.
AMD Secure Processor technology helps protect sensitive data and validate code before it is executed, protecting your system & data from unauthorised software and applications.
| W7900 | W7800 | W6800 | W7700 | W7600 | W7500 | W6400 | R9700 | |
|---|---|---|---|---|---|---|---|---|
| AEC / BIM | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✖ |
| CAD | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✖ |
| CAE / CFD | ✔ | ✔ | ✔ | ✖ | ✖ | ✖ | ✖ | ✖ |
| M&E | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✖ |
| RENDERING | ✔ | ✔ | ✔ | ✖ | ✖ | ✖ | ✖ | ✖ |
| VR | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✖ |
| ML / DL / AI | ✖ | ✖ | ✖ | ✖ | ✖ | ✖ | ✖ | ✔ |
The W7900 is the most powerful high-end card in the Radeon Pro W7000 range. Based on the RDNA 3 architecture, the W7900 has 6,144 stream processors, 192 AI accelerators and 96 ray accelerators plus 48GB of ultra-reliable GDDR6 ECC memory. The W7900 features 96MB of L3 Infinity Cache and supports four high resolution displays, making this card the perfect choice for very high-end workstations
Support for 8K video projects and up to six 4K HDR displays is enabled via AMD Infinity Cache technology, allowing data that is likely to be needed and reused, to be temporarily held in high-speed GPU memory.
The Ray Accelerator is a high-performance raytracing acceleration architecture. This specialised hardware handles the intersection of rays directly on AMD Radeon Pro GPUs.
AMD Radeon ReLive for VR technology means you have untethered freedom to naturally navigate your creations as you would in the real world - without worrying about wires, base stations or dedicated VR rooms.
Easily access the full GPU-accelerated experience of Radeon Pro graphics card-powered workstations from virtually anywhere with the remote workstation IP built into AMD Software Pro Edition.
The below table summarises each GPUs performance along with their technical specifications.
| Model | W7900 | W7800 | W7700 | W7600 | W7500 | W6400 | R9700 |
|---|---|---|---|---|---|---|---|
| Visualisation (X / 10) | 10 | 9 | 6 | 5 | 3 | 1 | 10 |
| Double Precision FP64 (TFLOPS) | 1.9 | 1.3 | 1.0 | 0.6 | 0.4 | 0.2 | N/A |
| Single Precision FP32 (TFLOPS) | 61.3 | 45.2 | 28.3 | 21.4 | 17.3 | 3.5 | 47.8 |
| Half Precision FP16 (TFLOPS) | 122.6 | 90.5 | 56.5 | 42.8 | 34.6 | 7.1 | 95.7 |
| AI INT4 (TOPS) | 245 | 181 | 113 | 86 | 69 | N/A | 1,531 |
| VR Ready | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| Architecture | RDNA3 | RDNA3 | RDNA3 | RDNA3 | RDNA3 | RDNA2 | RDNA 4 |
| GPU | Navi 31 | Navi 31 | Navi 32 | Navi 33 | Navi 33 | Navi 24 | Navi 48 |
| Stream Processors | 6,144 | 4,480 | 3,072 | 2,048 | 1,792 | 768 | 4,096 |
| AI Accelerators | 192 (1st Gen) | 140 (1st Gen) | 96 (1st Gen) | 64 (1st Gen) | 56 (1st Gen) | 0 | 128 (2nd Gen) |
| Ray Accelerators | 96 (2nd Gen) | 70 (2nd Gen) | 48 (2nd Gen) | 32 (2nd Gen) | 28 (2nd Gen) | 0 | 64 (3rd Gen) |
| Memory | 48GB GDDR6 | 32GB GDDR6 | 16GB GDDR6 | 8GB GDDR6 | 8GB GDDR6 | 4GB GDDR6 | 32GB GDDR6 |
| ECC Memory | ✔ | ✔ | ✔ | ✖ | ✖ | ✖ | TBC |
| Memory Controller | 384-bit | 256-bit | 256-bit | 128-bit | 128-bit | 64-bit | 256-bit |
| TDP | 295W | 260W | 190W | 130W | 70W | 50W | 300W |
| Minimum PSU | 750W | 700W | 650W | 500W | 450W | 450W | 750W |
| Release Date | Apr 2023 | Apr 2023 | Apr 2023 | Apr 2023 | Apr 2023 | Jan 2022 | July 2025 |
| Price |
|
|
|
|
Price TBC | ||
| BUY > | BUY > | BUY > | BUY > | BUY > | BUY > | BUY > |
All AMD workstation GPUs can be purchased standalone or integrated into a workstation from our 3XS Systems division. In addition, we can provide supported pricing for higher education and further education customers.
If you would still like some advice on configuring your ideal server, don’t hesitate to contact our friendly advisors on 01204 474747 or by contacting [email protected] .
The graphics card is the most important component in a workstation PC as its responsible for rendering applications, performing simulations and running AI models. More powerful, and more expensive, graphics cards enable you to work at higher resolutions as well as producing higher frame rates, improving user experience.
A graphics card comprises two main components, the GPU (Graphics Processing Unit), effectively the brain of the card plus VRAM (Video Random Access Memory) which the GPU uses to store data such as models, textures as well as buffering rendered frames.
A stream processor is the primary processor inside AMD Radeon GPUs responsible for rendering graphics and other tasks. Each GPUs has thousands of stream processors working together in parallel; the more cores, the higher the performance. Some tasks are accelerated by specialist ray accelerators or AI accelerators, see the separate entry in this FAQ for further detail on these types of core.
You can see how advanced a stream processor is by the name of the architecture, to name some recent examples RDNA 4 (2025), RDNA 3 (2023) and RDNA 2 (2022).
Ray accelerators work alongside stream processors inside AMD Radeon GPUs to accelerate ray traced effects in applications. Unlike traditional rasterised graphics, ray tracing simulates how light beams and shadows actually work, providing far more rich and realistic graphics. The more ray accelerators, the faster the framerate when ray tracing is enabled.
You can see how advanced the ray accelerators are in a GPU by its generation, i.e. 5th gen is more advanced than 4th gen etc.
AI accelerators work alongside stream processors inside AMD Radeon GPUs to accelerate AI workloads and applications. The more AI accelerators, the faster the AI performance will be.
You can see how advanced the AI accelerators are in a GPU by its generation, i.e. 5th gen is more advanced than 4th gen etc.
FSR (Fidelity Super Resolution) is an advanced AI-powered rendering technique unique to AMD graphics cards that uses the AI accelerators to increase frame rates. FSR enables you ramp up the resolution to enjoy higher quality graphics, without sacrificing performance.
A FLOP (Floating-Point Operation per Second) is a measure of how quickly GPUs calculate the complex floating-point maths behind complex calculations such as simulations and training AI models. The more FLOPS, the faster the performance.
Depending on the software, floating point calculations can be calculated to as great or little precision as required. This is commonly shorted to FPx where x is a number typically in the range of 4 to 64. See the separate entry in this FAQ for further detail.
Like other metrics in computer science such as KB, MB, GB and TB when it comes to RAM or storage, the number of FLOPS is commonly shortened to GFLOPS (giga, 10 to the power of 9), TFLOPS (tera, 10 to the power of 12) and PFLOPS (peta, 10 to the power of 15).
These are a shortened representation of how precisely a floating-point calculation is performed. The most common levels are in order of increasing precision:
| FP4 (1/8th precision) | FP8 (quarter precision) | FP16 (half-precision) | FP32 (single-precision) | FP64 (double precision) | |
|---|---|---|---|---|---|
| PRECISION |
chevron_left Least
Most chevron_right
|
||||
| PERFORMANCE |
chevron_left Fastest
Slowest chevron_right
|
||||
A TOP (Trillion Operations per Second) is a measure of how quickly a GPU can perform the integer maths that is commonly used when inferencing AI models. The more TOPS, the faster the performance.
