GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA GeForce RTX 5090 Founders Edition

Graphics processor

Video memory: 32 GB^*
Memory bus: 512 bit^*
Rated memory bandwidth: 1,790 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Blackwell 2.0^*
Process node: 5 nm^*
GPU cores: 21,760^*
Graphics interface: PCIe 5.0 x16^*
Reported chip die area: 750 mm²^*
Transistors: 92,200 million^*
GPU L2 cache: 96 MB^*
Graphics processor: GB202^*
Texture mapping units: 680^*
Raster output units: 176^*
Streaming multiprocessors: 170^*
Tensor cores: 680^*
Ray tracing cores: 170^*
Chip foundry: TSMC^*
Card or module format: Dual-slot^*
Declared GPU TDP: 575 W^*
Suggested system PSU: 950 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

Memory options: 32^*
Video memory: 32 GB^*
Video memory type: GDDR7^*
Memory bus: 512 bit^*
Rated memory bandwidth: 1,790 GB/s^*

Power specifications

Thermal design power: 575 W^*

System configuration

Detailed specifications

Specifications 1 · 31 fields

proc transistors: 92,200 million^*
proc die size: 750^* mm²
cores: 21,760^*
tensor cores: 680^*
rt cores: 170^*
sm count: 170^*
base clock: 2,017^*
boost clock: 2,407^*
memory clock: 1,750^*
ram: 32^*
name: NVIDIA GeForce RTX 5090 Founders Edition^*
ram type: GDDR7^*
bus width: 512^*
bus interface: PCIe 5.0 x16^*
ram bandwidth: 1.79 TB/s^*
fp16 performance: 104.8^*
fp32 performance: 104.8^*
fp64 performance: 1.637^*
tdp: 575^* W
suggested psu: 950^* W
slot width: Dual-slot^*
power connectors: 1x 16-pin^*
api cuda: 12^*
is retail board: Yes^*
gpi value: 44.04^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Blackwell 2.0^*
card release date: 2025-01-30^*
proc foundry: TSMC^*
proc process size: 5^* nm

Specifications 2 · 40 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^*

Architecture

Blackwell 2.0^*

Graphics interface

PCIe 5.0 x16^*

Memory bus

512^* bit

Reported shader processors

21,760^*

Reported theoretical FP16 peak

104.8^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

104.8^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

1.637^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

96 MB^*

Reported display outputs

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

Theoretical pixel fill rate

423.6 GPixel/s^*

External power connectors

1x 16-pin^*

Reported chip die area

750 mm²^*

Chip foundry

TSMC^*

Process node declaration

5 nm^*

Transistors

92,200 million^*

Graphics processor

GB202^*

Reported video memory

32^* GB

Rated memory bandwidth

1.79 TB/s^*

Video memory type

GDDR7^*

Raster output units

176^*

Ray tracing cores

170^*

Reported shading units

21,760^*

Card or module format

Dual-slot^*

Streaming multiprocessors

170^*

Suggested system PSU

950 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

575 W^*

Tensor cores

680^*

Theoretical texture fill rate

1,636.8 GTexel/s^*

Texture mapping units

680^*

GPU cores

21,760^*

Video memory

32^* GB

Video memory type

GDDR7^*

* Provisional data