Workstations for Topaz Video AI
Topaz Video AI is mainly GPU-bound, so the graphics card sets the pace. We size these machines around the GPU first, and add more cards for larger batches.
What matters for Topaz Video AI
- A fast NVIDIA GPU; the processor matters far less
- NVIDIA for the full Starlight model series
- 16GB of GPU memory runs every benchmark model
- Several GPUs, with a Pro licence, for batch work
Topaz Video is mainly GPU-bound: a Threadripper PRO is only about 10% faster than consumer processors. Cards with 16GB of memory run every benchmark model, and GPU memory above 48GB makes no difference. Only NVIDIA supports the full Starlight model series. With a Pro licence, Topaz staff say several GPUs can split a single video into blocks, or each GPU can take a separate file (Topaz community). We do not yet quote a multi-GPU speed-up. Standard and Heavy use one NVIDIA RTX PRO 4500 32GB or NVIDIA RTX PRO 5000 48GB in an Electron. Studio puts two NVIDIA RTX PRO 5000 48GB cards in an Atom for split or parallel jobs. Team fits four RTX PRO 6000 Max-Q 96GB cards in a Nano Pro as a batch machine for parallel clips.
Recommended configurations
Topaz Video AI – Standard
Electron · NVIDIA RTX PRO 4500 32GB
For a single artist or engineer
- CPU: AMD Ryzen 9 9950X3D
- RAM: 128GB DDR5 6000 2x64GB
- PCIe slots (16x): Nvidia RTX Pro 4500 Blackwell 32GB
- NVMe Storage (Gen 5.0): Samsung 9100 Pro Gen 5 2TB
- Operating System: Microsoft Windows 11 Pro
£11,537.75 inc VAT
£9,614.79 ex VAT
Built to order · dispatched in 4 working days
Topaz Video AI – Heavy
Electron · NVIDIA RTX PRO 5000 48GB
For professionals and freelancers
- CPU: AMD Ryzen 9 9950X3D
- RAM: 128GB DDR5 6000 2x64GB
- PCIe slots (16x): Nvidia RTX Pro 5000 Blackwell 48GB
- NVMe Storage (Gen 5.0): Samsung 9100 Pro Gen 5 4TB
- Operating System: Microsoft Windows 11 Pro
£15,270.19 inc VAT
£12,725.16 ex VAT
Built to order · dispatched in 11 working days
Topaz Video AI – Studio
Atom · 2× NVIDIA RTX PRO 5000 48GB
For studios and small teams
- CPU: AMD Ryzen Threadripper 9970X 32 Core
- RAM: 4 × 64GB RDIMM ECC DDR5 6400
- PCIe slots (16x): 2 × Nvidia RTX Pro 5000 Blackwell 48GB
- NVMe M.2 Drives (Gen 5): Samsung 9100 Pro Gen 5 4TB
- Operating System: Microsoft Windows 11 Pro
£35,963.07 inc VAT
£29,969.24 ex VAT
Built to order · dispatched in 11 working days
Topaz Video AI – Team
Nano Pro · 4x NVIDIA RTX PRO 6000 Max-Q 96GB
For large teams and enterprise
- CPU: AMD Ryzen Threadripper PRO 9965WX 24 Core
- RAM: 8 × 32GB RDIMM ECC DDR5 6400
- PCIe Options: 4 × Nvidia RTX Pro 6000 Blackwell Max-Q 96GB
- NVMe M.2 Drives (Gen 5): Samsung 9100 Pro Gen 5 8TB
- Operating System: Microsoft Windows 11 Pro
£91,991.98 inc VAT
£76,659.98 ex VAT
Built to order · dispatched in 12 working days
Each recommended system is a starting point. Select Customise to add components or change the specification before you order.
Tell us what you need for Topaz Video AI
Share the models you use, your source and output resolutions and how many clips you process. We will review the right configuration and confirm availability before you order.
Frequently asked questions
With a Pro licence, Topaz staff say multiple GPUs can split a single video into blocks, or each GPU can process a separate file (Topaz community). We cannot yet say how much faster one video renders on two or four cards.
For the full Starlight model series, yes. Only NVIDIA supports all Starlight models. Every configuration here uses NVIDIA.
Topaz recommends 8GB (Topaz Labs). In practice, 16GB cards run every benchmark model and memory above 48GB makes no difference.
Not for speed alone. A Threadripper PRO is only about 10% faster than consumer processors, so a consumer-class CPU is acceptable. Spend on the GPU first.
Standard suits occasional upscaling and restoration. Heavy moves to one NVIDIA RTX PRO 5000 48GB, as much GPU memory as Topaz Video benefits from. Studio adds a second card for split or parallel jobs. Team is for studios processing many clips at once.
Talk to someone at Renderboxes
Not sure which build is right? Speak to our team and we will help you choose the right configuration for your work.
Send us an enquiry
Tell us what you are working on and we will recommend a configuration.
Contact us