NVIDIA RTX 2000 Ada 16GB

Ada Lovelace PCIe 2024 4nm

Overview

12.0

FP32 TFLOPS

16 GB

Memory GDDR6

224 GB/s

Memory Bandwidth

70 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	0.2	N/A	64	Standard
FP32	12.0	N/A	32	Standard
TF32	12.0	not published	32	Standard
BF16	24.0	not published	16	Standard
FP16	24.0	not published	16	Standard
FP8	48.0	not published	8	Standard
FP6	—	not published	—	Standard
FP4	—	not published	—	Standard
INT8	48.0	not published	8	Standard

Memory Specifications

Capacity: 16 GB
Type: GDDR6
Bandwidth: 224 GB/s
Interface Width: 128-bit

Power & Efficiency

TDP: 70 W
Max power (Flopper estimate): ~81 W est.
FP32 dense TFLOPS per W of TDP: 0.17 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 0.34 TFLOPS/W

Flopper estimate: 70 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: 2024

Variant: 16GB

Compute Engine

CUDA Cores: 2,816

Tensor Cores: 88 (4th Gen)

SMs: 22

Base Clock: 1.64 GHz

Boost Clock: 2.13 GHz

Interconnect

PCIe: 4.0 x8

Enterprise Features

Sparsity: Yes