The FP16 row carries only the sparse figure NVIDIA published, 272.8 TFLOPS, and its dense half is deliberately blank. On Ampere GA10x, dense FP16 is 4x FP32 on professional parts and 2x on GeForce parts with FP32 accumulate, and BOTH buckets produce an 8x-FP32 sparse headline, so the printed 272.8 does not identify which applies. NVIDIA's GA102 whitepaper prints per-SKU tables for five parts and no RTX A-series card is among them. Rather than publish a coin flip as a fact, this catalog leaves the dense value unset.

NVIDIA RTX A5500 24GB

Ampere PCIe 2022 8nm Spec confidence: Official
FP32
34
TFLOPS
VRAM
24 GB
GDDR6
Bandwidth
768 GB/s
memory
TDP
230 W
148.3 TFLOPS/kW
Download datasheet

Overview

The NVIDIA RTX A5500 slots between the RTX A5000 and the RTX A6000, with 10,240 CUDA cores, 320 third-generation Tensor cores and 80 second-generation RT cores, and 24 GB of GDDR6 with ECC on a 384-bit bus at 768 GB/s. That is the same memory subsystem as the RTX A6000, at half the frame buffer, and it is what makes the card interesting second hand: 768 GB/s is well ahead of the 24 GB Ada workstation cards that replaced it. It draws 230 W from a single 8-pin connector and delivers 34.1 TFLOPS of FP32. Two cards join over an NVLink bridge for 48 GB of pooled memory at 112.5 GB/s, a feature NVIDIA removed from the Ada generation entirely, so this remains one of the last professional cards where memory pooling across a pair is possible.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
64-bit floating point
0.5TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
34TFLOPS 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 273TFLOPS
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

2022

Process Node

8nm

Memory

24 GB GDDR6

Bandwidth

768 GB/s

TDP

230 W

Max Power

230 W

Interconnect

113 GB/s NVLink

CUDA Cores

10,240

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 10,240
Tensor Cores 320 (3rd Gen)
Streaming Multiprocessors 80
Memory
VRAM 24 GB
Memory Type GDDR6
Bandwidth 768 GB/s
Interface Width 384-bit
Interconnect & I/O
GPU-to-GPU NVLink
Interconnect Bandwidth 113 GB/s
Interconnect Links 2
PCIe 4.0 x16
Power & Thermal
TDP 230 W
Max Board Power 230 W
Power Connector 1x 8-pin PCIe
Cooling Active
Enterprise Features
ECC Memory Yes
Sparsity Yes
Compute APIs CUDA 11.6, OpenCL 3.0, DirectCompute
Physical & Media
Card Length 266.7 mm
Width 2-slot
NVENC Engines 1
NVDEC Engines 2
General
Form Factor PCIe
Architecture Ampere
Process Node 8nm
Launch Year 2022

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2022-03-01

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 A5500 have?

The NVIDIA RTX A5500 delivers 34 TFLOPS FP32 and 273 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 A5500?

The NVIDIA RTX A5500 has a TDP (Thermal Design Power) rating of 230 watts.

How much memory does the NVIDIA RTX A5500 have?

The NVIDIA RTX A5500 is equipped with 24 GB of VRAM with 768 GB/s of memory bandwidth.

What architecture is the NVIDIA RTX A5500 based on?

The NVIDIA RTX A5500 is based on the Ampere architecture, launched in 2022.

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