This is the original 6 GB card announced in August 2021. NVIDIA later shipped a 12 GB revision of the same board, which is already in this catalog as nvidia-rtx-a2000-12gb; the two are identical apart from frame buffer, so a listing that says only "RTX A2000" needs its memory size checked. As with the RTX A5500, the FP16 row carries only the sparse figure NVIDIA published and its dense half is left blank on purpose.

NVIDIA RTX A2000 6GB

Ampere PCIe 2021 8nm Spec confidence: Official
FP32
8
TFLOPS
VRAM
6 GB
GDDR6
Bandwidth
288 GB/s
memory
TDP
70 W
114.3 TFLOPS/kW
Download datasheet

Overview

The NVIDIA RTX A2000 was the first low-profile professional Ampere card, packing 3,328 CUDA cores, 104 third-generation Tensor cores and 26 second-generation RT cores with 6 GB of GDDR6 and ECC into a 70 W half-height dual-slot board with no supplementary power connector. It delivers 8.0 TFLOPS of FP32 on a 192-bit bus at 288 GB/s. Six gigabytes is tight for anything but small models today, which is why NVIDIA followed it with a 12 GB revision, but the card remains common in small form factor workstations and edge boxes where nothing larger will physically fit. Four Mini DisplayPort 1.4a connectors handle display output, and a single encode and single decode engine handle video.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
0.1TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
8TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
BF16
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP16
16-bit floating point
The vendor publishes only the 2:4 sparse figure for this precision 64TFLOPS
FP8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP6
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP4
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
INT8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision

Specifications

Architecture

Ampere

Form Factor

PCIe

Launch Year

2021

Process Node

8nm

Memory

6 GB GDDR6

Bandwidth

288 GB/s

TDP

70 W

Max Power

70 W

CUDA Cores

3,328

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 3,328
Tensor Cores 104 (3rd Gen)
Streaming Multiprocessors 26
Memory
VRAM 6 GB
Memory Type GDDR6
Bandwidth 288 GB/s
Interface Width 192-bit
Interconnect & I/O
PCIe 4.0 x16
Power & Thermal
TDP 70 W
Max Board Power 70 W
Cooling Active
Enterprise Features
ECC Memory Yes
Sparsity Yes
Compute APIs CUDA 11.6, OpenCL 3.0, DirectCompute
Physical & Media
Card Length 167.6 mm
Width 2-slot
NVENC Engines 1
NVDEC Engines 1
General
Form Factor PCIe
Architecture Ampere
Process Node 8nm
Launch Year 2021

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2021-08-01

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
3 of 9
Normalization
All values in TFLOPS

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

NVIDIA RTX A6000 48GB

PCIe · 2020
FP32: 39 TFLOPS
Compare vs RTX A6000

NVIDIA A40 48GB

PCIe · 2021
FP32: 37 TFLOPS
Compare vs A40

NVIDIA A10G 24GB

PCIe · 2022
FP32: 35 TFLOPS
Compare vs A10G

Frequently Asked Questions

How many TFLOPS does the NVIDIA RTX A2000 have?

The NVIDIA RTX A2000 delivers 8 TFLOPS FP32 and 64 TFLOPS FP16 (2:4 sparse) at peak. Flopper does not currently have a verified FP8 throughput figure for it.

What is the power consumption of the NVIDIA RTX A2000?

The NVIDIA RTX A2000 has a TDP (Thermal Design Power) rating of 70 watts.

How much memory does the NVIDIA RTX A2000 have?

The NVIDIA RTX A2000 is equipped with 6 GB of VRAM with 288 GB/s of memory bandwidth.

What architecture is the NVIDIA RTX A2000 based on?

The NVIDIA RTX A2000 is based on the Ampere architecture, launched in 2021.

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs