NVIDIA GeForce RTX 3080 10GB

Ampere PCIe 2020 8nm

Overview

29.8

FP32 TFLOPS

10 GB

Memory GDDR6X

760 GB/s

Memory Bandwidth

320 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	0.5	N/A	64	Standard
FP32	29.8	N/A	32	Standard
TF32	29.8	59.5	32	Standard
BF16	59.5	119.0	16	Standard
FP16	59.5	119.0	16	Standard
FP8	—	not published	—	Standard
FP6	—	not published	—	Standard
FP4	—	not published	—	Standard
INT8	238.0	476.0	8	Standard
INT4	476.0	952.0	4	Standard

Memory Specifications

Capacity: 10 GB
Type: GDDR6X
Bandwidth: 760 GB/s
Interface Width: 320-bit

Power & Efficiency

TDP: 320 W
Max power (Flopper estimate): ~368 W est.
FP32 dense TFLOPS per W of TDP: 0.09 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.19 TFLOPS/W

Flopper estimate: 320 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: Ampere

Process Node: 8nm

Form Factor: PCIe

Launch Year: 2020

Variant: 10GB

Compute Engine

CUDA Cores: 8,704

Tensor Cores: 272 (3rd Gen)

SMs: 68

Base Clock: 1.44 GHz

Boost Clock: 1.71 GHz

Chip Design

Transistors: 28.3 billion

Die Size: 628 mm²

Enterprise Features

Sparsity: Yes