Flopper.io
Flopper.io GPU Datasheet

NVIDIA GeForce RTX 4080 16GB Datasheet

Ada Lovelace PCIe 2022 4nm

Overview

48.7
FP32 TFLOPS
16 GB
Memory
717 GB/s
Memory Bandwidth
320 W
TDP

Performance Metrics

PrecisionPeak (dense)2:4 SparseBitsType
FP640.7N/A64Standard
FP3248.7N/A32Standard
TF3248.7not published32Standard
BF1697.5not published16Standard
FP1697.5not published16Standard
FP8195.0not published8Standard
FP6—not published—Standard
FP4—not published—Standard
INT8389.9779.88Standard

Memory Specifications

Capacity
16 GB
Type
—
Bandwidth
717 GB/s
Interface Width
—

Power & Efficiency

TDP
320 W
Max power (Flopper estimate)
~368 W est.
FP32 dense TFLOPS per W of TDP
0.15 TFLOPS/W
FP16 dense TFLOPS per W of TDP
0.30 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: Ada Lovelace
Process Node: 4nm
Form Factor: PCIe
Launch Year: 2022
Variant: 16GB

Enterprise Features

Sparsity: Yes