GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA RTX A5000-8Q

Graphics processor

Video memory: 8 GB^*
Memory bus: 384 bit^*
Rated memory bandwidth: 768 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ampere^*
Process node: 8 nm^*
GPU cores: 8,192^*
Graphics interface: PCIe 4.0 x16^*
Reported chip die area: 628 mm²^*
Transistors: 28,300 million^*
GPU L2 cache: 6 MB^*
Graphics processor: GA102^*
Texture mapping units: 256^*
Raster output units: 96^*
Streaming multiprocessors: 64^*
Tensor cores: 256^*
Ray tracing cores: 64^*
Chip foundry: Samsung^*
Card or module format: Dual-slot^*
Declared GPU TDP: 230 W^*
Suggested system PSU: 550 W^*
External power connectors: 1x 8-pin^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 8.6^*
Shader model: 6.9^*

Memory & storage

Memory options: 8^*
Video memory: 8 GB^*
Video memory type: GDDR6^*
Memory bus: 384 bit^*
Rated memory bandwidth: 768 GB/s^*

Power specifications

Thermal design power: 230 W^*

System configuration

Detailed specifications

Specifications 1 · 31 fields

Specifications 2 · 40 fields

CUDA compute capability

8.6^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Architecture

Ampere^*

Graphics interface

PCIe 4.0 x16^*

Memory bus

384^* bit

Reported shader processors

8,192^*

Reported theoretical FP16 peak

27.77^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

27.77^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.4339^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

6 MB^*

Reported display outputs

4x DisplayPort 1.4a^*

Theoretical pixel fill rate

162.7 GPixel/s^*

External power connectors

1x 8-pin^*

Reported chip die area

628 mm²^*

Chip foundry

Samsung^*

Process node declaration

8 nm^*

Transistors

28,300 million^*

Graphics processor

GA102^*

Reported video memory

8^* GB

Rated memory bandwidth

768.0 GB/s^*

Video memory type

GDDR6^*

Raster output units

96^*

Ray tracing cores

64^*

Reported shading units

8,192^*

Card or module format

Dual-slot^*

Streaming multiprocessors

64^*

Suggested system PSU

550 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

230 W^*

Tensor cores

256^*

Theoretical texture fill rate

433.9 GTexel/s^*

Texture mapping units

256^*

GPU cores

8,192^*

Video memory

8^* GB

Video memory type

GDDR6^*

* Provisional data