GPU Wiki

Compare GPUs

Pick up to four GPUs and compare their specs row by row. Specs that mean different things across generations are kept apart.

Popular comparisons

Add a third or fourth GPU
Spec CMP 40HX
Overview
Product name NVIDIA CMP 40HX
Architecture Turing
Generation / family Mining GPUs
GPU codename TU106
Launch date 2021-02-18
Market segment Desktop in Mining GPUs
Board type / entry type Reference GPU
GPU
Process node TSMC 12 nm
Die size 445 mm²
Transistor count 10.8 billion
GPU chip TU106
SM / multiprocessor count 36
CUDA Cores 2304
Tensor Cores 288
RT Cores 36
ROPs 64
TMUs 144
Clocks
Base / Core clock 1,470 MHz
Boost clock 1,650 MHz
Memory clock 1,750 MHz
Memory
Memory size 8 GB
Memory type GDDR6
Memory bus width 256-bit
Memory bandwidth 448 GB/s
Bus / Interface
Bus interface PCIe 1.0 x4
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 185 W
Recommended PSU 450 W
Power connectors 1x 8-pin
Slot width Dual-slot, 229 mm length, 35 mm width
Features
DirectX support DirectX 12.2
OpenGL support OpenGL 4.6
Vulkan support Vulkan 1.4
CUDA support 7.5
Shader Model 6.8
Ray tracing support Hardware RT units present
Performance / Benchmarks
FP32 throughput 7.6 TFLOPS
FP16 throughput 15.21 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

DLAA counts as native resolution; DLSS, FSR and XeSS upscaling never do. A ray tracing setting without a readable on or off value is read as on.