CMP 70HX

GPU Code: GA104

8 GB

GDDR6X

1395 MHz

Boost Clock

8 nm

Process
Share on Social Media
Share CMP 70HX specifications with others

Technical Specifications

Core Specifications
Architecture: Ampere
Process Size: 8 nm
Base Clock: 1365 MHz
Boost Clock: 1395 MHz
Shader Units: 3840
SMs: 30
Tensor Cores: 120
RT Cores: 30
TMUs: 120
ROPs: 64
Memory & Performance
Memory Size: 8 GB
Memory Type: GDDR6X
Memory Bandwidth: 608.3 GB/s
Bus Interface: PCIe 1.0 x4
Suggested PSU: 200 W
Cache & Die Information
L1 Cache: 128 KB
L2 Cache: 4.0 MB
Die Size: 392 mm²
Transistors: 17.4 billion
Transistor Density: 44.4 million/mm²

API Support

DirectX
12.2
OpenGL
4.6
Vulkan
1.3
Cuda Compute
8.6 sm_86

Physical Specifications

Board Length: 267 mm
Board Width: 112 mm
Power Connectors: 1x 12-pin

Quick Facts

Release Date: 2021-01-01
Manufacturer: NVIDIA
Generation: Mining GPUs

Performance

Pixel Fill Rate 89.3 GPixel/s
Texture Fill Rate 167.4 GTexel/s
FP32 Performance 10.7 TFLOPS

CUDA Toolkit Compatibility

Cuda Compute
8.6 sm_86
Architecture

Ampere

Supported CUDA Toolkits
11.1 11.2 11.3 11.4 11.5 11.6 11.7 11.8 12.0 12.1 12.2 12.3 12.4 12.5 12.6 12.7 12.8

Ampere architecture with 2nd gen RT cores and hardware AV1 decode