(Image credit: Videocardz)
- AMD Radeon AI PRO R9700S delivers 47.8 TFLOPS peak FP32 compute power
- AMD equips the R9700S with 32GB GDDR6 memory for AI workloads
- PCIe 5.0 x16 support enables high-bandwidth communication for AI applications
AMD has introduced the Radeon AI PRO R9700S, a passively cooled workstation GPU that joins the R9000 series and promises enterprise-level AI performance.
After the launch of this series earlier this year, [several major brands confirmed products featuring R9700 cards](https://www.techradar.com/pro/here-are-all-the-radeon-ai-pro-r9700-cards-that-have-been-announc…
(Image credit: Videocardz)
- AMD Radeon AI PRO R9700S delivers 47.8 TFLOPS peak FP32 compute power
- AMD equips the R9700S with 32GB GDDR6 memory for AI workloads
- PCIe 5.0 x16 support enables high-bandwidth communication for AI applications
AMD has introduced the Radeon AI PRO R9700S, a passively cooled workstation GPU that joins the R9000 series and promises enterprise-level AI performance.
After the launch of this series earlier this year, several major brands confirmed products featuring R9700 cards, indicating strong industry adoption.
The R9700S keeps the same Navi 48 RDNA4 configuration as the standard R9700, offering 64 compute units and 4096 stream processors.
Passive cooling for high-density AI workloads
Its boost clock reaches up to 2920MHz and delivers a peak FP32 throughput of 47.8 TFLOPS, which makes it a capable option for enterprise AI workloads.
Designed for dense racks and multi-GPU setups, the R9700S uses a 32GB GDDR6 memory buffer on a 256-bit bus with 64MB Infinity Cache.
PCIe 5.0 x16 support ensures high-bandwidth communication with compatible workstation platforms.
The “S” designation in the R9700S indicates a silent design, which replaces the blower-style cooler of previous models.
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
This approach uses system airflow rather than onboard fans, making the GPU suitable for compact racks where multiple cards operate closely.
Despite the passive cooling, the card keeps a 300W TDP and draws power through a single 12V-2x6 connector.
This approach reflects AMD’s focus on maintaining compute performance without adding active components.
The company also launched the R9600D, which scales down to 48 compute units and 3072 stream processors while keeping identical memory.
However, the R9700S offers higher throughput for large AI models.
Both cards support Linux ECC memory options and are fully compatible with AMD’s Software PRO Edition and ROCm integration.
The R9700S is optimized for tasks such as generative AI inference and training of large language models.
This lets enterprises offload demanding workloads from CPU cores to GPU accelerators.
Early adoption of the R9700 has appeared in prebuilt systems like Elsa’s Veluga-D A70S G6 workstation.
It pairs the GPU with an AMD Ryzen 7 9700X CPU, 64GB of DDR5 RAM, and PCIe expansion slots for additional accelerators.
With these chips, AMD offers enterprise-ready solutions for AI computation while keeping a focus on memory bandwidth, power delivery, and silent operation.
That said, the high raw performance of this chip raises questions about sustained thermals in dense deployments.
Therefore, enterprises that deploy multiple units must consider airflow and system-level heat management to maintain stability under peak AI workloads.
Via Videocardz
Follow TechRadar on Google News and* add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!*
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.
Efosa has been writing about technology for over 7 years, initially driven by curiosity but now fueled by a strong passion for the field. He holds both a Master’s and a PhD in sciences, which provided him with a solid foundation in analytical thinking.