GPU Wiki
Compare NVIDIA 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.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
| Spec | CMP 70HX |
|---|---|
| Overview | |
| Product name | NVIDIA CMP 70HX |
| Architecture | Ampere |
| Generation / family | Mining GPUs |
| GPU codename | GA104 |
| Launch date | 2021-01-01 |
| Market segment | Desktop in Mining GPUs |
| Board type / entry type | Reference GPU |
| GPU | |
| Process node | Samsung 8 nm |
| Die size | 392 mm² |
| Transistor count | 17.4 billion |
| GPU chip | GA104 |
| SM / multiprocessor count | 30 |
| CUDA Cores | 3840 |
| Tensor Cores | 120 |
| RT Cores | 30 |
| ROPs | 64 |
| TMUs | 120 |
| Clocks | |
| Base / Core clock | 1,365 MHz |
| Boost clock | 1,395 MHz |
| Memory clock | 1,188 MHz |
| Memory | |
| Memory size | 8 GB |
| Memory type | GDDR6X |
| Memory bus width | 256-bit |
| Memory bandwidth | 608.3 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 1.0 x4 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| Recommended PSU | 200 W |
| Power connectors | 1x 12-pin |
| Slot width | Dual-slot, 267 mm length |
| Features | |
| DirectX support | DirectX 12.2 |
| OpenGL support | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 |
| CUDA support | 8.6 |
| Shader Model | 6.8 |
| Ray tracing support | Hardware RT units present |
| Performance / Benchmarks | |
| FP32 throughput | 10.71 TFLOPS |
| FP16 throughput | 10.71 TFLOPS |
Overview
Product name
CMP 70HX
NVIDIA CMP 70HX
Architecture
CMP 70HX
Ampere
Generation / family
CMP 70HX
Mining GPUs
GPU codename
CMP 70HX
GA104
Launch date
CMP 70HX
2021-01-01
Market segment
CMP 70HX
Desktop in Mining GPUs
Board type / entry type
CMP 70HX
Reference GPU
GPU
Process node
CMP 70HX
Samsung 8 nm
Die size
CMP 70HX
392 mm²
Transistor count
CMP 70HX
17.4 billion
GPU chip
CMP 70HX
GA104
SM / multiprocessor count
CMP 70HX
30
CUDA Cores
CMP 70HX
3840
Tensor Cores
CMP 70HX
120
RT Cores
CMP 70HX
30
ROPs
CMP 70HX
64
TMUs
CMP 70HX
120
Clocks
Base / Core clock
CMP 70HX
1,365 MHz
Boost clock
CMP 70HX
1,395 MHz
Memory clock
CMP 70HX
1,188 MHz
Memory
Memory size
CMP 70HX
8 GB
Memory type
CMP 70HX
GDDR6X
Memory bus width
CMP 70HX
256-bit
Memory bandwidth
CMP 70HX
608.3 GB/s
Bus / Interface
Bus interface
CMP 70HX
PCIe 1.0 x4
AGP / PCI / PCIe distinction
CMP 70HX
PCIe
Power
Recommended PSU
CMP 70HX
200 W
Power connectors
CMP 70HX
1x 12-pin
Slot width
CMP 70HX
Dual-slot, 267 mm length
Display / Media
Features
DirectX support
CMP 70HX
DirectX 12.2
OpenGL support
CMP 70HX
OpenGL 4.6
Vulkan support
CMP 70HX
Vulkan 1.4
CUDA support
CMP 70HX
8.6
Shader Model
CMP 70HX
6.8
Ray tracing support
CMP 70HX
Hardware RT units present
Performance / Benchmarks
FP32 throughput
CMP 70HX
10.71 TFLOPS
FP16 throughput
CMP 70HX
10.71 TFLOPS