- Nvidia RTX Pro 4000 SFF delivers over the double of AI performance for its predecessor
- Nvidia claims that RTX Pro 2000 surpasses RTX A2000 in 3D modeling performance
- Both new GPUs maintain a 70-watt limit that enables implementation in space-limited systems
NVIDIA has launched two new SFF (SMALL Form Factor Ready) RTX PRO servers and workstation GPUs built on its blackwell architecture using a single fan, fan style, low-profile design.
The new RTX Pro 4000 SFF and RTX Pro 2000 slot under the top-end RTX Pro 6000, but is designed to maintain a strong performance for professional workloads in smaller, lower power work station.
Both GPUs aim to switch more treatment from CPU to GPU, which allows even small form factor work stations to handle AI inference, reproduction and simulation faster than before.
Compact hardware with capacity at workstation level
The RTX Pro 4000 SFF is built with 24 GB ECC GDDR7 memory and delivers up to 770 AI tops.
NVIDIA says it offers more than twice as much as the AI performance for the previous generation of the RTX A4000 SFF, and has also improved radiation tracking, 50% more memory bandwidth and has a 70W thermal limit, making it suitable for work stations with limited cooling capacity.
RTX Pro 2000, also limited to 70W, carries 16 GB ECC GDDR7 memory and 545 AI tops of flow.
Nvidia claims it is approx. 1.5 times faster than RTX A2000 in 3D modeling, CAD and reproduction.
The company also points to its applicability in AI-driven image and text generation, which potentially speeds up design and content work in smaller studios or engineering team.
These workstations GPUs share backwell architecture benefits found in Nvidia’s larger RTX Pro-Lineup, including support for FP4 precision through the fifth generation of tenses and other generation of transformer engine.
This is intended to improve the performance of inference while the power consumption holds power consumption.
Nvidia has not yet revealed specific pricing for these models, but has indicated that it will make them available through partners such as PNY, TD Synnex, Dell, HP and Lenovo later this year.
Given their position under the RTX Pro 6000, they are expected to cost significantly less, while still providing a large benefit increase compared to previous GPUs with small format.
While marketing as an upgrade path for professionals, the actual advantage depends on the fastest CPU-only small workstation configurations of work load type and software optimization to GPU acceleration.
For tasks that already benefit from GPU calculation, such as AI-inference, large-scale reproduction and simulation, the new RTX Pro 4000 SFF and RTX Pro 2000 could offer strong gains without requiring a larger, more expensive workstation.
For CPU-focused applications, the improvements may be less dramatic, but the added GPU capacity is still expanding the benefit confining for small, power-limited systems.
