AMD Announces Radeon AI PRO R9700 Pricing at $1299 and Reveals Launch Date

In just a few days, the highly anticipated RDNA 4 AI GPU will officially make its debut, with the confirmed retail price aligning with previous speculations.

AMD Confirms Launch Date and Pricing for Radeon AI Pro R9700

AMD has announced that its most capable RDNA 4 workstation GPU, the Radeon AI Pro R9700, will be available starting on October 27th. The announcement was made today, following its unveiling at Computex five months ago. The official manufacturer’s suggested retail price (MSRP) for the R9700 is set at $1, 299. This aligns with earlier forecasts, and there was a brief listing for the ASRock Creator Radeon AI Pro R9700 at $1, 329 on a retail website.

AMD Radeon AI Pro R9700 graphics card with AMD RDNA4 architecture, 32GB GDDR6 memory, available October 27 from $1, 299.

Unlike previous models, the Radeon AI Pro R9700 will be distributed exclusively through AMD’s board partners, as the company will not offer a reference design. Some partners may only sell the card through system integrators; for instance, XFX has noted this on its official page. Key specifications reveal that the R9700 utilizes the NAVI 48 die, inheriting the architecture of RDNA 4 found in the prominent gaming Radeon RX 9070 XT. Both GPUs share the same fundamentals, including 4096 Stream Processors, 128 Render Output Units (ROPs), and the same count of Ray Tracing (RT) Cores.

However, a significant upgrade lies in the VRAM specifications; the Radeon AI Pro R9700 offers double the memory compared to the RX 9070 XT. As a dedicated workstation GPU engineered for advanced AI tasks, it incorporates enhanced memory modules resulting in 32 GB of GDDR6 VRAM, supported by a 256-bit memory bus. This makes it the most economical 32 GB workstation GPU currently available.

Powered by AMD RDNA™ 4 architecture, the Radeon AI PRO R9700 enables medium to large AI models to run directly on local workstations. Combined with AMD ROCm™ open software support, the card accelerates large language models, diffusion models, and other compute-intensive workflows, bringing data-center-class efficiency to the desktop.

– AMD

According to AMD, the Radeon AI Pro R9700 excels with performance two times faster than the W7800 in DeepSeek R1 benchmarks, comfortably managing Large Language Models (LLMs) and text-to-image AI tasks. AMD has previously highlighted the advantages of its 32 GB of VRAM when compared to high-end alternatives like the GeForce RTX 5080, which only supports 16 GB. Moreover, the R9700 supports Multi-GPU configurations via AMD ROCm, facilitating high-throughput AI workloads crucial for local workstations. Its compact design features a dual-slot layout with a blower-style cooler designed for efficient airflow, ideal for setups requiring expanded memory capacities.

Source & Images