GPU Wiki

Compare GPUs

Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.

Popular comparisons

Add a third or fourth GPU
Spec Jetson AGX Xavier 32 GB
Overview
Product name NVIDIA Jetson AGX Xavier 32 GB
Architecture Volta
Generation / family Tegra
GPU codename GV10B
Launch date 2018-10-01
Market segment Embedded, SoC in Tegra
Board type / entry type Other
GPU
Process node TSMC 12 nm
Die size 350 mm²
Transistor count 9 billion
GPU chip GV10B
SM / multiprocessor count 8
CUDA Cores 512
Tensor Cores 64
ROPs 16
TMUs 32
Clocks
Base / Core clock 854 MHz
Boost clock 1,377 MHz
Memory clock 2,133 MHz
Memory
Memory size 32 GB
Memory type LPDDR4X
Memory bus width 256-bit
Memory bandwidth 136.5 GB/s
Bus / Interface
Bus interface PCIe 4.0 x4
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 30 W
Slot width IGP, 100 mm length
Features
DirectX support DirectX 12.1
OpenGL support OpenGL 4.6
Vulkan support Vulkan 1.2
CUDA support 7.2
Shader Model 6.0
Performance / Benchmarks
FP32 throughput 1.41 TFLOPS
FP16 throughput 2.82 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.