NVIDIA GeForce RTX 5080 16GB

Blackwell PCIe 2025 4nm

Overview

56.3

FP32 TFLOPS

16 GB

Memory GDDR7

960 GB/s

Memory Bandwidth

360 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	0.9	N/A	64	Standard
FP32	56.3	N/A	32	Standard
TF32	56.3	112.6	32	Standard
BF16	112.6	225.1	16	Standard
FP16	225.1	not published	16	Standard
FP8	450.2	not published	8	Standard
FP6	—	not published	—	Standard
FP4	900.5	not published	4	Standard
INT8	450.2	not published	8	Standard

Memory Specifications

Capacity: 16 GB
Type: GDDR7
Bandwidth: 960 GB/s
Interface Width: 256-bit

Power & Efficiency

TDP: 360 W
Max power (Flopper estimate): ~414 W est.
FP32 dense TFLOPS per W of TDP: 0.16 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.63 TFLOPS/W

Flopper estimate: 360 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: 16GB

Compute Engine

CUDA Cores: 10,752

Tensor Cores: 336 (5th Gen)

SMs: 84

Base Clock: 2.29 GHz

Boost Clock: 2.62 GHz

Chip Design

Transistors: 45.6 billion

Die Size: 378 mm²

Enterprise Features

Sparsity: Yes