NVIDIA CMP 30HX videocard review

CMP 30HX videocard released by NVIDIA; release date: 25 Feb 2021. The videocard is based on Turing microarchitecture codenamed TU116.

Core clock speed - 1530 MHz. Boost clock speed - 1785 MHz. Texture fill rate - 157.1 GTexel/s. Pipelines - 1408. Manufacturing process technology - 12 nm. Transistors count - 6600 million. Power consumption (TDP) - 125 Watt.

Memory type: GDDR6. Maximum RAM amount - 6 GB. Memory bus width - 192 bit. Memory clock speed - 1750 MHz, 14 Gbps effective. Memory bandwidth - 336.0 GB/s.

Benchmarks

Geekbench
OpenCL

Top 1 GPU

This GPU

345150

68128

Name	Value
Geekbench - OpenCL	68128

Specifications (specs)

Essentials
Architecture	Turing
Code name	TU116
Launch date	25 Feb 2021
Place in performance rating	298
Technical info
Boost clock speed	1785 MHz
Core clock speed	1530 MHz
Manufacturing process technology	12 nm
Pipelines	1408
Pixel fill rate	85.68 GPixel/s
Texture fill rate	157.1 GTexel/s
Thermal Design Power (TDP)	125 Watt
Transistor count	6600 million

Video outputs and ports
Display Connectors	No outputs
Compatibility, dimensions and requirements
Form factor	Dual-slot
Height	35 mm, 1.4 inches
Interface	PCIe 3.0 x4
Length	229 mm, 9 inches
Recommended system power (PSU)	300 Watt
Supplementary power connectors	1x 8-pin
Width	111 mm, 4.4 inches
API support
DirectX	12 (12_1)
OpenCL	3.0
OpenGL	4.6
Shader Model	6.7
Vulkan
Memory
Maximum RAM amount	6 GB
Memory bandwidth	336.0 GB/s
Memory bus width	192 bit
Memory clock speed	1750 MHz, 14 Gbps effective
Memory type	GDDR6