GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA RTX PRO 500 Blackwell Embedded

Graphics processor

Video memory: 6 GB^*
Memory bus: 96 bit^*
Rated memory bandwidth: 288 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Blackwell 2.0^*
Process node: 5 nm^*
GPU cores: 1,792^*
Graphics interface: PCIe 5.0 x16^*
Reported chip die area: 149 mm²^*
Transistors: 16,900 million^*
GPU L2 cache: 24 MB^*
Graphics processor: GB207^*
Texture mapping units: 56^*
Raster output units: 24^*
Streaming multiprocessors: 14^*
Tensor cores: 56^*
Ray tracing cores: 14^*
Chip foundry: TSMC^*
Card or module format: IGP^*
Declared GPU TDP: 35 W^*
External power connectors: None^*
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

Memory options: 6^*
Video memory: 6 GB^*
Video memory type: GDDR7^*
Memory bus: 96 bit^*
Rated memory bandwidth: 288 GB/s^*

Power specifications

Thermal design power: 35 W^*

System configuration

Detailed specifications

Specifications 1 · 28 fields

proc transistors: 16,900 million^*
proc die size: 149^* mm²
cores: 1,792^*
tensor cores: 56^*
rt cores: 14^*
sm count: 14^*
base clock: 2,160^*
boost clock: 2,565^*
memory clock: 1,500^*
ram: 6^*
name: NVIDIA RTX PRO 500 Blackwell Embedded^*
ram type: GDDR7^*
bus width: 96^*
bus interface: PCIe 5.0 x16^*
ram bandwidth: 288^* GB/s
fp16 performance: 9.193^*
fp32 performance: 9.193^*
fp64 performance: 0.1436^*
tdp: 35^* W
slot width: IGP^*
api cuda: 12^*
is retail board: No^*
gpi value: 5.27^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Blackwell 2.0^*
proc foundry: TSMC^*
proc process size: 5^* nm

Specifications 2 · 39 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

18.39^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Graphics interface

PCIe 5.0 x16^*

Memory bus

96^* bit

Reported shader processors

1,792^*

Reported theoretical FP16 peak

9.193^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

9.193^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.1436^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

24 MB^*

Reported display outputs

Portable Device Dependent^*

Theoretical pixel fill rate

61.56 GPixel/s^*

External power connectors

None^*

Reported chip die area

149 mm²^*

Chip foundry

TSMC^*

Process node declaration

5 nm^*

Transistors

16.9 billion^*

Graphics processor

GB207^*

Reported video memory

6^* GB

Rated memory bandwidth

288.0 GB/s^*

Video memory type

GDDR7^*

Raster output units

24^*

Ray tracing cores

14^*

Reported shading units

1,792^*

Card or module format

IGP^*

Streaming multiprocessors

14^*

Declared GPU TDP

35 W^*

Tensor cores

56^*

Theoretical texture fill rate

143.6 GTexel/s^*

Reported theoretical TF32 peak

9.193^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Texture mapping units

56^*

GPU cores

1,792^*

Video memory

6^* GB

Video memory type

GDDR7^*

* Provisional data