NVIDIA GeForce RTX 5090 32GB

Blackwell PCIe 2025 4nm

Overview

104.8

FP32 TFLOPS

32 GB

Memory GDDR7

1.8 TB/s

Memory Bandwidth

575 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	1.6	N/A	64	Standard
FP32	104.8	N/A	32	Standard
TF32	104.8	209.5	32	Standard
BF16	209.5	419.0	16	Standard
FP16	419.1	not published	16	Standard
FP8	838.2	not published	8	Standard
FP6	—	not published	—	Standard
FP4	1676.0	not published	4	Standard
INT8	838.2	not published	8	Standard

Memory Specifications

Capacity: 32 GB
Type: GDDR7
Bandwidth: 1.8 TB/s
Interface Width: 512-bit

Power & Efficiency

TDP: 575 W
Max power (Flopper estimate): ~661 W est.
FP32 dense TFLOPS per W of TDP: 0.18 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.73 TFLOPS/W

Flopper estimate: 575 W TDP x 1.15. The vendor publishes no maximum board power for this part. Per W of TDP figures divide dense peak by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead.

Hardware Details

Vendor: NVIDIA

Architecture: Blackwell

Process Node: 4nm

Form Factor: PCIe

Launch Year: 2025

Variant: 32GB

Compute Engine

CUDA Cores: 21,760

Tensor Cores: 680 (5th Gen)

SMs: 170

Base Clock: 2.01 GHz

Boost Clock: 2.41 GHz

Chip Design

Transistors: 92.0 billion

Die Size: 750 mm²

Enterprise Features

Sparsity: Yes