GeekRadar / The comparison desk
COMPARE.
GPUGIGABYTE Radeon PRO W7900 Dual Slot AI TOP
Graphics processor
- Video memory
- 48 GB*
- Memory bus
- 384 bit*
- Rated memory bandwidth
- 864 GB/s*
No matched benchmark results are available for this entry yet.
Processing & platform
- Architecture
- RDNA 3.0*
- Process node
- 5 nm*
- GPU cores
- 6,144*
- Graphics interface
- PCIe 4.0 x16*
- Reported chip die area
- 529 mm²*
- Transistors
- 57,700 million*
- GPU L2 cache
- 6 MB*
- Graphics processor
- Navi*
- Texture mapping units
- 384*
- Raster output units
- 192*
- Ray tracing cores
- 96*
- Chip foundry
- TSMC*
- Card or module format
- Dual-slot*
- Declared GPU TDP
- 295 W*
- Suggested system PSU
- 600 W*
- External power connectors
- 2x 8-pin*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenGL
- 4.6*
- OpenCL
- 2.0*
- Vulkan
- 1.4*
- Shader model
- 6.9*
Memory & storage
- Memory options
- 48*
- Video memory
- 48 GB*
- Video memory type
- GDDR6*
- Memory bus
- 384 bit*
- Rated memory bandwidth
- 864 GB/s*
Power specifications
- Thermal design power
- 295 W*
System configuration
Detailed specifications
Specifications 1 · 27 fields
- proc transistors
- 57,700 million*
- proc die size
- 529* mm²
- cores
- 6,144*
- rt cores
- 96*
- base clock
- 1,855*
- boost clock
- 2,495*
- memory clock
- 2,250*
- ram
- 48*
- name
- GIGABYTE Radeon PRO W7900 Dual Slot AI TOP*
- ram type
- GDDR6*
- bus width
- 384*
- bus interface
- PCIe 4.0 x16*
- ram bandwidth
- 864* GB/s
- fp16 performance
- 122.6*
- fp32 performance
- 61.32*
- fp64 performance
- 1.916*
- tdp
- 295* W
- suggested psu
- 600* W
- slot width
- Dual-slot*
- power connectors
- 2x 8-pin*
- is retail board
- Yes*
- gpi value
- 29.28*
- manufacturer
- GIGABYTE*
- arch name
- RDNA 3.0*
- card release date
- 2023-04-13*
- proc foundry
- TSMC*
- proc process size
- 5* nm
Specifications 2 · 37 fields
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenCL
- 2.0*
- OpenGL
- 4.6*
- Shader model
- 6.9*
- Vulkan
- 1.4*
- Reported theoretical BF16 peak
- 122.6* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Graphics interface
- PCIe 4.0 x16*
- Memory bus
- 384* bit
- Reported shader processors
- 6,144*
- Reported theoretical FP16 peak
- 61.32* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP32 peak
- 61.32* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP64 peak
- 1.916* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Declared L1 cache configuration
- 256 KB per Array*
- Declared GPU L2 cache
- 6 MB*
- Reported display outputs
- 3x DisplayPort 2.1, 1x mini-DisplayPort 2.1*
- Theoretical pixel fill rate
- 479.0 GPixel/s*
- External power connectors
- 2x 8-pin*
- Reported chip die area
- 529 mm²*
- Chip foundry
- TSMC*
- Process node declaration
- 5 nm*
- Transistors
- 57.7 billion*
- Graphics processor
- Navi*
- Reported video memory
- 48* GB
- Rated memory bandwidth
- 864.0 GB/s*
- Video memory type
- GDDR6*
- Raster output units
- 192*
- Ray tracing cores
- 96*
- Reported shading units
- 6,144*
- Card or module format
- Dual-slot*
- Suggested system PSU
- 600 W*
- 2:4 tensor sparsity
- No*
- Declared GPU TDP
- 295 W*
- Theoretical texture fill rate
- 958.1 GTexel/s*
- Texture mapping units
- 384*
- GPU cores
- 6,144*
- Video memory
- 48* GB
- Video memory type
- GDDR6*
0 selected Compare 0
* Provisional data