GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA GeForce RTX 5070 GB203

Graphics processor

Video memory: 12 GB^*
Memory bus: 192 bit^*
Rated memory bandwidth: 672 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Process node: 5 nm^*
GPU cores: 6,144^*
Graphics interface: PCIe 5.0 x16^*
Reported chip die area: 378 mm²^*
Transistors: 45,600 million^*
GPU L2 cache: 48 MB^*
Graphics processor: GB203^*
Texture mapping units: 192^*
Raster output units: 80^*
Streaming multiprocessors: 48^*
Tensor cores: 192^*
Ray tracing cores: 48^*
Chip foundry: TSMC^*
Card or module format: Dual-slot^*
Declared GPU TDP: 250 W^*
Suggested system PSU: 600 W^*
External power connectors: 1x 16-pin^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 12.0^*
Shader model: 6.9^*

Memory & storage

Video memory: 12 GB^*
Video memory type: GDDR7^*
Memory bus: 192 bit^*
Rated memory bandwidth: 672 GB/s^*

System configuration

Detailed specifications

Specifications · 37 fields

CUDA compute capability

12.0^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Reported theoretical BF16 peak

61.73^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Graphics interface

PCIe 5.0 x16^*

Memory bus

192^* bit

Reported shader processors

6,144^*

Reported theoretical FP16 peak

30.87^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

30.87^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.4823^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

48 MB^*

Reported display outputs

1x HDMI 2.1b, 3x DisplayPort 2.1b^*

Theoretical pixel fill rate

201.0 GPixel/s^*

External power connectors

1x 16-pin^*

Reported chip die area

378 mm²^*

Chip foundry

TSMC^*

Process node declaration

5 nm^*

Transistors

45.6 billion^*

Graphics processor

GB203^*

Reported video memory

12^* GB

Rated memory bandwidth

672.0 GB/s^*

Video memory type

GDDR7^*

Raster output units

80^*

Ray tracing cores

48^*

Reported shading units

6,144^*

Card or module format

Dual-slot^*

Streaming multiprocessors

48^*

Suggested system PSU

600 W^*

Declared GPU TDP

250 W^*

Tensor cores

192^*

Theoretical texture fill rate

482.3 GTexel/s^*

Reported theoretical TF32 peak

30.87^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Texture mapping units

192^*

* Provisional data