AMD Launches Radeon AI PRO R9700 GPU Featuring 32 GB VRAM, 128 AI Cores, and 300W TDP: Doubles Performance of Previous Generation W7800 in DeepSeek R1

AMD has unveiled its latest innovation: the Radeon AI PRO R9700 GPU. This cutting-edge graphics card is specifically designed for the artificial intelligence domain, boasting an impressive 32 GB of VRAM and performance that is double that of its predecessor.

Introducing the AMD Radeon AI PRO R9700 GPU: A Game Changer in AI-Optimized Performance

The newly launched Radeon AI PRO R9700 marks AMD’s first entry into the RDNA 4 GPU lineup, designed exclusively for AI applications. This revolutionary card represents a significant shift, replacing the older Radeon WX and Radeon PRO series with the new Radeon AI PRO branding.

Featuring specifications that mirror the RX 9070 XT, the R9700 is optimized for AI workloads. It harnesses the Navi 48 architecture, equipped with 64 compute units and 4, 096 stream processors. Additionally, it includes 128 AI accelerators and has a total board power (TBP) of 300W.

Specifications of AMD Radeon AI PRO R9700

In terms of memory capabilities, the Radeon AI PRO R9700 is outfitted with 32 GB of GDDR6 memory operating across a 256-bit bus, effectively doubling the VRAM available on the 9070 XT. Performance metrics provided by AMD indicate that the GPU offers 96 TFLOPs of FP16 compute and an impressive 1531 TOPS for INT4 (sparse) operations.

The strategic design of the R9700 aims to facilitate the efficient execution of advanced AI models. With the 32 GB of VRAM, the GPU is equipped to handle demanding local AI tasks, including applications like DeepSeek R1 Distill Qwen 32B Q6, Mistral Small 3.1 24B Instruct 2503 Q8, Flux 1 Schnel, and SD 3.5 Medium.

Performance comparisons reveal that the Radeon AI PRO R9700 outperforms the Radeon PRO W7800 32 GB GPU by a factor of two in scenarios involving DeepSeek R1. Furthermore, AMD has highlighted the advantages of the R9700 over the RTX 5080, which is limited by its 16 GB VRAM, showcasing performance improvements of up to five times in memory-intensive AI applications.

Moreover, the AMD Radeon AI PRO R9700 supports scaling through a 4-way Multi-GPU configuration on a PCIe 5.0 platform, allowing users to utilize a substantial 128 GB of VRAM. This setup is crucial for handling buffer models like Mistral 123B and DeepSeek R1 70B, which can require upwards of 112-116 GB of VRAM.

The AMD Radeon AI PRO R9700 is set for release in July 2025 and will be available from prominent manufacturers including ASUS, ASRock, Gigabyte, PowerColor, Sapphire, XFX, and Yeston. This dual-slot graphics card will feature a blower cooler design.

AMD Radeon Pro Workstation Graphics Lineup

Graphics Card Name	Radeon R9700	Radeon Pro W7900	Radeon Pro W7800	Radeon Pro W6900X	Radeon Pro W6800	Radeon Pro VII	Radeon Pro W5700X	Radeon Pro W5700	Radeon Pro WX 9100	Radeon Pro WX 8200	Radeon Pro WX 7100
GPU	Navi 48	Navi 31	Navi 31	Navi 21	Navi 21	Vega 20	Navi 10	Navi 10	Vega 10	Vega 10	Polaris 10
Process Node	4nm	5nm+6nm	5nm+6nm	7nm	7nm	7nm	7nm	7nm	14nm	14nm	14nm
Compute Units	64 CU	96 CU	70 CU	80	60	60	40	36	64	56	36
Stream Processors	4096	6144	4480	5120	3840	3840	2560	2304	4096	3584	2304
Clock Speed (Peak)	TBD	~2.5 GHz	~2.5 GHz	2171 MHz	2320 MHz	1700 MHz	2040 MHz	1930 MHz	1500 MHz	1500 MHz	1243 MHz
VRAM	32GB GDDR6	48GB GDDR6	32GB GDDR6	32GB GDDR6	32GB GDDR6	16 GB HBM2	16GB GDDR6	8GB GDDR6	16 GB HBM2	8 GB HBM2	8 GB GDDR5
Memory Bandwidth	640GB/s	864 GB/s	576 GB/s	512GB/s	512GB/s	1024 GB/s	448 GB/s	448 GB/s	512GB/s	484GB/s	224 GB/s
Memory Bus	256-bit	384-bit	256-bit	256-bit	256-bit	4096-bit	256-bit	256-bit	2048-bit	2048-bit	256-bit
Compute Rate (FP32)	48 TFLOPs	61.3 TFLOPs	45.2 TFLOPs	22.23 TFLOPs	17.82 TFLOPs	13.1 TFLOPs	9.5 TFLOPs	8.89 TFLOPs	12.3 TFLOPs	10.8 TFLOPs	5.7 TFLOPs
TDP	300W	295W	260W	300W	250W	250W	240W	205W	250W	230W	150W
Price	TBD	$3999 US	$2499 US	$5999 US	$2249 US	$1899 US	$999 US	$799 US	$2199 US	$999 US	$799 US
Launch	2025	2023	2023	2021	2021	2020	2019	2019	2017	2018	2016