Report an Error

AMD Radeon AI PRO R9700

Graphics Processor
Navi 48
Cores
4096
TMUs
256
ROPs
128
Memory Size
32 GB
Memory Type
GDDR6
Bus Width
256 bit
GPU Chip
GPU
This product is not released yet.
Data on this page may change in the future.
The Radeon AI PRO R9700 will be a professional graphics card by AMD, that is expected to launch in July 2025. Built on the 4 nm process, and based on the Navi 48 graphics processor, in its Navi 48 XTW variant, the card supports DirectX 12 Ultimate. The Navi 48 graphics processor is a large chip with a die area of 357 mm² and 53,900 million transistors. It features 4096 shading units, 256 texture mapping units, and 128 ROPs. Also included are 128 tensor cores which help improve the speed of machine learning applications. The card also has 64 raytracing acceleration cores. AMD has paired 32 GB GDDR6 memory with the Radeon AI PRO R9700, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1660 MHz, which can be boosted up to 2920 MHz, memory is running at 2518 MHz (20.1 Gbps effective).
Being a dual-slot card, the AMD Radeon AI PRO R9700 draws power from 1x 16-pin power connector, with power draw rated at 300 W maximum. Display outputs include: 4x DisplayPort 2.1a. Radeon AI PRO R9700 is connected to the rest of the system using a PCI-Express 5.0 x16 interface. The card's dimensions are 267 mm x 111 mm x 40 mm, and it features a dual-slot cooling solution.

Graphics Processor

GPU Name
Navi 48
GPU Variant
Navi 48 XTW
Architecture
RDNA 4.0
Foundry
TSMC
Process Type
N4P FinFET
Process Size
4 nm
Transistors
53,900 million
Density
151.0M / mm²
Die Size
357 mm²
Chip Package
Monolithic

Graphics Card

Release Date
Jul 2025
Announced
May 20th, 2025
Generation
Radeon Pro Navi
(Navi IV Series)
Predecessor
Radeon Pro Vega
Production
Unreleased
Bus Interface
PCIe 5.0 x16

Relative Performance

GeForce 210
0%
GeForce 9400 GT
1%
Radeon HD 4550
1%
Radeon HD 5450
1%
Radeon HD 6450
1%
GeForce GT 520
1%
GeForce GT 220
1%
GeForce GT 430
2%
Radeon HD 5570
2%
Radeon HD 4670
2%
GeForce GT 440
2%
GeForce GT 240
2%
GeForce 9600 GT
2%
Radeon HD 5670
2%
GeForce GT 640
3%
GeForce 9800 GT
3%
Radeon HD 6670
3%
Radeon HD 4830
3%
Radeon HD 4770
3%
Radeon HD 4850
3%
GeForce GTS 250
3%
GeForce GTS 450
3%
Radeon HD 5750
3%
Radeon HD 7750
4%
Radeon HD 5770
4%
GeForce GTX 260
4%
Radeon HD 4870
4%
Radeon Vega 8
4%
GeForce GTX 550 Ti
4%
GeForce GTX 650
4%
Radeon HD 5830
4%
Radeon HD 6790
5%
Radeon HD 4890
5%
GeForce GTX 460
5%
Radeon RX Vega 11
5%
GeForce GT 1030
5%
GeForce GTX 275
5%
Radeon HD 7770 GHz Edition
5%
GeForce GTX 280
5%
GeForce GTX 465
5%
Radeon HD 6850
5%
GeForce GTX 285
6%
Radeon HD 5850
6%
GeForce GTX 650 Ti
6%
Radeon HD 7790
6%
Radeon RX 550
6%
GeForce GTX 470
6%
Radeon HD 6870
7%
Radeon HD 5870
7%
GeForce GTX 560 Ti
7%
Radeon HD 4870 X2
7%
GeForce GTX 750 Ti
7%
Radeon HD 6950
7%
GeForce GTX 295
8%
GeForce GTX 650 Ti Boost
8%
Radeon HD 7850
8%
GeForce GTX 480
8%
Radeon HD 6970
8%
Radeon R7 265
9%
Radeon R7 370
9%
Radeon RX 460
9%
GeForce GTX 660
9%
GeForce GTX 570
9%
Radeon RX 560
9%
GeForce GTX 950
9%
Radeon HD 7870 GHz Edition
9%
Radeon R9 270X
10%
GeForce GTX 660 Ti
10%
GeForce GTX 580
10%
GeForce GTX 1050
10%
Radeon HD 7950
10%
GeForce GTX 1630
10%
Radeon HD 5970
10%
GeForce GTX 760
10%
GeForce GTX 670
11%
GeForce GTX 960
12%
Radeon R9 380
12%
Radeon R9 285
12%
Radeon HD 7970
12%
GeForce GTX 680
12%
GeForce GTX 1050 Ti
12%
GeForce GTX 770
13%
Radeon HD 6990
13%
Radeon R9 280X
13%
GeForce GTX 590
14%
Radeon HD 7970 GHz Edition
14%
GeForce GTX 780
15%
Arc A380
15%
Radeon RX 6400
15%
GeForce GTX 1650
16%
Radeon RX 470
17%
Radeon R9 290
17%
Radeon RX 570
18%
Radeon R9 390
18%
Radeon R9 290X
18%
GeForce GTX 970
18%
GeForce GTX TITAN
18%
GeForce GTX 780 Ti
19%
Radeon R9 390X
19%
Radeon HD 7990
19%
Radeon RX 480
19%
GeForce GTX 690
19%
GeForce GTX 1060 6 GB
20%
Radeon RX 5500 OEM
20%
Radeon RX 580
20%
Radeon RX 5500 XT
21%
Radeon RX 6500 XT
21%
GeForce GTX 980
21%
GeForce GTX 1650 SUPER
21%
Radeon R9 FURY
21%
Radeon RX 590
22%
Radeon R9 295X2
23%
GeForce GTX 1660
23%
Radeon R9 FURY X
24%
GeForce GTX 980 Ti
24%
GeForce GTX TITAN X
25%
GeForce GTX 1660 SUPER
25%
GeForce GTX 1070
27%
GeForce GTX 1660 Ti
27%
GeForce RTX 3050 8 GB
27%
Radeon RX Vega 56
28%
GeForce GTX 1070 Ti
30%
Radeon RX 5600 XT
31%
Radeon RX Vega 64
31%
GeForce GTX 1080
32%
GeForce RTX 2060
32%
Radeon RX 5700
33%
Arc A580
33%
Radeon RX 6600
34%
GeForce RTX 2060 SUPER
35%
GeForce RTX 2070
36%
Radeon RX 5700 XT
36%
GeForce RTX 3060 12 GB
37%
Arc A750
38%
Radeon VII
38%
TITAN X Pascal
39%
Radeon RX 6600 XT
39%
GeForce GTX 1080 Ti
40%
Arc A770
41%
GeForce RTX 2070 SUPER
41%
GeForce RTX 4060
41%
Radeon RX 7600
42%
Radeon RX 6650 XT
43%
GeForce RTX 2080
44%
Radeon RX 7600 XT
44%
GeForce RTX 3060 Ti
46%
GeForce RTX 2080 SUPER
46%
Arc B580
46%
GeForce RTX 4060 Ti 8 GB
47%
Radeon RX 6700 XT
49%
GeForce RTX 5060 Ti 8 GB
49%
Radeon RX 7700 XT
51%
Radeon RX 6750 XT
52%
GeForce RTX 3070
52%
GeForce RTX 2080 Ti
52%
GeForce RTX 3070 Ti
55%
GeForce RTX 5060 Ti 16 GB
59%
Radeon RX 6800
59%
Radeon RX 6800 XT
67%
GeForce RTX 4070
67%
Radeon RX 7800 XT
71%
Radeon RX 6900 XT
71%
GeForce RTX 3080
73%
Radeon RX 6950 XT
75%
Radeon RX 7900 GRE
77%
GeForce RTX 3080 Ti
77%
GeForce RTX 4070 SUPER
78%
GeForce RTX 3090
81%
GeForce RTX 5070
83%
GeForce RTX 4070 Ti
83%
Radeon RX 9070
91%
GeForce RTX 4070 Ti SUPER
91%
Radeon RX 7900 XT
93%
GeForce RTX 3090 Ti
94%
Radeon AI PRO R9700
100%
Radeon RX 9070 XT
102%
GeForce RTX 5070 Ti
106%
Radeon RX 7900 XTX
108%
GeForce RTX 4080
108%
GeForce RTX 4080 SUPER
109%
GeForce RTX 5080
122%
GeForce RTX 4090
141%
GeForce RTX 5090
185%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
1660 MHz
Game Clock
2350 MHz
Boost Clock
2920 MHz
Memory Clock
2518 MHz
20.1 Gbps effective

Memory

Memory Size
32 GB
Memory Type
GDDR6
Memory Bus
256 bit
Bandwidth
644.6 GB/s

Render Config

Shading Units
4096
TMUs
256
ROPs
128
Compute Units
64
Tensor Cores
128
RT Cores
64
L0 Cache
32 KB per WGP
L2 Cache
8 MB
L3 Cache
64 MB

Theoretical Performance

Pixel Rate
373.8 GPixel/s
Texture Rate
747.5 GTexel/s
FP16 (half)
95.68 TFLOPS (2:1)
FP32 (float)
47.84 TFLOPS
FP64 (double)
1,495 GFLOPS (1:32)

Board Design

Slot Width
Dual-slot
Length
267 mm
10.5 inches
Width
111 mm
4.4 inches
Height
40 mm
1.6 inches
TDP
300 W
Suggested PSU
700 W
Outputs
4x DisplayPort 2.1a
Power Connectors
1x 16-pin

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.2
Vulkan
1.3
Shader Model
6.8

Navi 48 GPU Notes

Generation: Navi IV
Codename:
Ray Tracing Cores: 3rd Gen
Matrix Cores: 3rd Gen
Infinity Cache: 3rd Gen
Graphics/Compute: 12.0.1
Shader ISA: GFX12.0 (gfx1201)
Display Core Next: 3.2.0
Video Core Next: 4.0.0
System DMA: 6.0.0

Retail boards based on this design (1)

Name GPU Clock Boost Clock Memory Clock Other Changes
1660 MHz 2920 MHz 2518 MHz 1x HDMI 3x DisplayPort
May 24th, 2025 10:33 CDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts