AMD Unleashes Radeon AI PRO R9700 GPU With 32 GB VRAM, 128 AI Cores & 300W TDP: 2x Faster Than Last-Gen W7800 In DeepSeek R1

May 20, 2025 at 11:00pm EDT

AMD is unleashing its brand-new Radeon AI PRO R9700 GPU, which is aimed purely at the AI segment with 32 GB of VRAM, and performance twice that of the previous gen.

AMD's Radeon AI PRO R9700 GPU Aims To Offer AI Leadership In Its Price Segment With 32 GB VRAM & 1531 TOPS Performance

Well, as expected, AMD has introduced its first RDNA 4 GPU with 32 GB of VRAM, aimed purely at the AI segment. With this new offering, AMD is also unveiling its brand-new product branding, Radeon AI PRO. The new series replaces the older Radeon WX & Radeon PRO offerings.

Related Story AMD’s Frank Azor Pushes Back on FSR 4.1 Cancellation Rumor for RDNA 3.5 iGPUs, Says No Such Decision Has Been Made

The first product within the lineup is the AMD Radeon AI PRO R9700 which features the same exact specifications as the RX 9070 XT, but optimized for AI workloads. The chip being used is the Navi 48 which comes with 64 compute units or 4096 stream processors. The GPU is loaded with 128 AI accelerators and has a TBP of up to 300W.

In terms of memory, the AMD Radeon AI PRO R9700 is equipped with 32 GB of GDDR6 memory, running across a 256-bit bus and this essentially doubles the VRAM featured on the 9070 XT. Other performance aspects being shared by AMD include the 96 TFLOPs of FP16 compute and 1531 TOPS INT4 (Sparse).

The goal of the AMD Radeon AI PRO R9700 GPU is to enable high-quality AI models to be completed efficiently. That's why it has been equipped with 32 GB of VRAM, which is an optimal amount for most advanced Local AI workloads, such as DeepSeek R1 Distill Qwen 32B Q6, Mistral Small 3.1 24B Instruct 2503 Q8, Flux 1 Schnel, and SD 3.5 Medium.

As for performance, AMD states that the Radeon AI PRO R9700 is twice as fast as the Radeon PRO W7800 32 GB GPU in DeepSeek R1, while the company also shows a few measurements against the RTX 5080, which features a 16 GB VRAM buffer. The 16 GB of VRAM might not be suitable for AI models that require more memory, and that's why the R9700 is being shown to be up to 5x faster.

But it doesn't end here; the AMD Radeon AI PRO R9700 can also be scaled in 4-way Multi-GPU configurations using a modern-day PCIe 5.0 platform. This enables users to harness a massive 128 GB pool, which can handle buffer models such as Mistral 123B & DeepSeek R1 70B. These models can consume up to 112-116 GB of VRAM.

Lastly, for availability, the AMD Radeon AI PRO R9700 GPU will be available in July this year through leading partners such as ASUS, ASRock, Gigabyte, PowerColor, Sapphire, XFX, and Yeston. The card is going to be a dual-slot design with a blower cooler.

AMD Radeon Pro Workstation Graphics Lineup:

Graphics Card NameRadeon AI PRO R9700Radeon Pro W7900Radeon Pro W7800Radeon Pro W6900XRadeon Pro W6800Radeon Pro VIIRadeon Pro W5700XRadeon Pro W5700Radeon Pro WX 9100Radeon Pro WX 8200Radeon Pro WX 7100
GPUNavi 48Navi 31Navi 31Navi 21Navi 21Vega 20Navi 10Navi 10Vega 10Vega 10Polaris 10
Process Node4nm5nm+6nm5nm+6nm7nm7nm7nm7nm7nm14nm14nm14nm
Compute Units64 CU96 CU70 CU8060604036645636
Stream Processors40966144448051203840384025602304409635842304
Clock Speed (Peak)TBD~2.5 GHz~2.5 GHz2171 MHz2320 MHz1700 MHz2040 MHz1930 MHz1500 MHz1500 MHz1243 MHz
VRAM32 GB GDDR648 GB GDDR632 GB GDDR632 GB GDDR632 GB GDDR616 GB HBM216 GB GDDR68 GB GDDR616 GB HBM28 GB HBM28 GB GDDR5
Memory Bandwidth640 GB/s864 GB/s576 GB/s512 GB/s512 GB/s1024 GB/s448 GB/s448 GB/s512 GB/s484 GB/s224 GB/s
Memory Bus256-bit384-bit256-bit256-bit256-bit4096-bit256-bit256-bit2048-bit2048-bit256-bit
Compute Rate (FP32)48 TFLOPs61.3 TFLOPs45.2 TFLOPs22.23 TFLOPs17.82 TFLOPs13.1 TFLOPs9.5 TFLOPs8.89 TFLOPs12.3 TFLOPs10.8 TFLOPs5.7 TFLOPs
TDP300W295W260W300W250W250W240W205W250W230W150W
PriceTBD$3999 US$2499 US$5999 US$2249 US$1899 US$999 US$799 US$2199 US$999 US$799 US
Launch20252023202320212021202020192019201720182016

About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.

Follow Wccftech on Google to get more of our news coverage in your feeds.