GeekRadar / The comparison desk
COMPARE.
GPUAMD Xbox Series X 6nm GPU
Graphics processor
- Video memory
- 10 GB*
- Memory bus
- 320 bit*
- Rated memory bandwidth
- 560 GB/s*
No matched benchmark results are available for this entry yet.
Processing & platform
- Architecture
- RDNA 2.0*
- Process node
- 6 nm*
- GPU cores
- 3,328*
- Transistors
- 15,300 million*
- GPU L2 cache
- 5 MB*
- Graphics processor
- Scarlett*
- Texture mapping units
- 208*
- Raster output units
- 64*
- Chip foundry
- TSMC*
- Declared GPU TDP
- 200 W*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenGL
- 4.6*
- OpenCL
- 1.2*
- Vulkan
- 1.2*
- Shader model
- 6.8*
Memory & storage
- Memory options
- 10*
- Video memory
- 10 GB*
- Video memory type
- GDDR6*
- Memory bus
- 320 bit*
- Rated memory bandwidth
- 560 GB/s*
Power specifications
- Thermal design power
- 200 W*
System configuration
Detailed specifications
Specifications 1 · 20 fields
- proc transistors
- 15,300 million*
- cores
- 3,328*
- memory clock
- 1,750*
- ram
- 10*
- name
- AMD Xbox Series X 6nm GPU*
- ram type
- GDDR6*
- bus width
- 320*
- ram bandwidth
- 560* GB/s
- fp16 performance
- 24.29*
- fp32 performance
- 12.15*
- fp64 performance
- 0.7592*
- tdp
- 200* W
- is retail board
- No*
- gpi value
- 8.55*
- vendor
- amd*
- manufacturer
- AMD*
- arch name
- RDNA 2.0*
- card release date
- 2024-10-15*
- proc foundry
- TSMC*
- proc process size
- 6* nm
Specifications 2 · 29 fields
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenCL
- 1.2*
- OpenGL
- 4.6*
- Shader model
- 6.8*
- Vulkan
- 1.2*
- Memory bus
- 320* bit
- Reported shader processors
- 3,328*
- Reported theoretical FP16 peak
- 24.29* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP32 peak
- 12.15* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP64 peak
- 0.7592* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Declared GPU L2 cache
- 5 MB*
- Reported display outputs
- 1x HDMI 2.1*
- Theoretical pixel fill rate
- 116.8 GPixel/s*
- Chip foundry
- TSMC*
- Process node declaration
- 6 nm*
- Transistors
- 15,300 million*
- Graphics processor
- Scarlett*
- Reported video memory
- 10* GB
- Rated memory bandwidth
- 560.0 GB/s*
- Video memory type
- GDDR6*
- Raster output units
- 64*
- Reported shading units
- 3,328*
- 2:4 tensor sparsity
- No*
- Declared GPU TDP
- 200 W*
- Theoretical texture fill rate
- 379.6 GTexel/s*
- Texture mapping units
- 208*
- GPU cores
- 3,328*
- Video memory
- 10* GB
- Video memory type
- GDDR6*
0 selected Compare 0
* Provisional data