GeekRadar / The comparison desk
COMPARE.
GPU
ASROCK

ASRock Radeon AI PRO R9700 Creator

Graphics processor

Video memory
32 GB*
Memory bus
256 bit*
Rated memory bandwidth
644.60 GB/s*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture
RDNA 4.0*
Process node
4 nm*
GPU cores
4,096*
Graphics interface
PCIe 5.0 x16*
Reported chip die area
357 mm²*
Transistors
53,900 million*
GPU L2 cache
8 MB*
Graphics processor
Navi*
Texture mapping units
256*
Raster output units
128*
Ray tracing cores
64*
Chip foundry
TSMC*
Card or module format
Dual-slot*
Declared GPU TDP
300 W*
Suggested system PSU
700 W*
External power connectors
1x 16-pin*
DirectX / feature level
12 Ultimate (12_2)*
OpenGL
4.6*
OpenCL
2.2*
Vulkan
1.4*
Shader model
6.8*

Memory & storage

Memory options
32*
Video memory
32 GB*
Video memory type
GDDR6*
Memory bus
256 bit*
Rated memory bandwidth
644.60 GB/s*

Power specifications

Thermal design power
300 W*

System configuration

Detailed specifications

Specifications 1 · 27 fields
proc transistors
53,900 million*
proc die size
357* mm²
cores
4,096*
rt cores
64*
base clock
1,660*
boost clock
2,920*
memory clock
2,518*
ram
32*
name
ASRock Radeon AI PRO R9700 Creator*
ram type
GDDR6*
bus width
256*
bus interface
PCIe 5.0 x16*
ram bandwidth
644.6* GB/s
fp16 performance
95.68*
fp32 performance
47.84*
fp64 performance
1.495*
tdp
300* W
suggested psu
700* W
slot width
Dual-slot*
power connectors
1x 16-pin*
is retail board
Yes*
gpi value
21.76*
manufacturer
ASROCK*
arch name
RDNA 4.0*
card release date
2025-07-23*
proc foundry
TSMC*
proc process size
4* nm
Specifications 2 · 36 fields
DirectX / feature level
12 Ultimate (12_2)*
OpenCL
2.2*
OpenGL
4.6*
Shader model
6.8*
Vulkan
1.4*
Architecture
RDNA 4.0*
Graphics interface
PCIe 5.0 x16*
Memory bus
256* bit
Reported shader processors
4,096*
Reported theoretical FP16 peak
95.68* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP32 peak
47.84* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP64 peak
1.495* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Declared GPU L2 cache
8 MB*
Reported display outputs
Active
4x DisplayPort 2.1a*
Struck-out declarations
  • 1x HDMI 2.1b, 3x DisplayPort 2.1a*
Theoretical pixel fill rate
373.8 GPixel/s*
External power connectors
1x 16-pin*
Reported chip die area
357 mm²*
Chip foundry
TSMC*
Process node declaration
4 nm*
Transistors
53,900 million*
Graphics processor
Navi*
Reported video memory
32* GB
Rated memory bandwidth
644.6 GB/s*
Video memory type
GDDR6*
Raster output units
128*
Ray tracing cores
64*
Reported shading units
4,096*
Card or module format
Dual-slot*
Suggested system PSU
700 W*
2:4 tensor sparsity
No*
Declared GPU TDP
300 W*
Theoretical texture fill rate
747.5 GTexel/s*
Texture mapping units
256*
GPU cores
4,096*
Video memory
32* GB
Video memory type
GDDR6*

* Provisional data