GPU Benchmarks NVIDIA A100 80 GB (PCIe) vs. NVIDIA H100 NVL (PCIe) vs. NVIDIA RTX 6000 Ada

Quick links:

Best GPUs for deep learning, AI development, compute in 2023–2024. Recommended GPU & hardware for AI training, inference (LLMs, generative AI). GPU training, inference benchmarks using PyTorch, TensorFlow for computer vision (CV), NLP, text-to-speech, etc.

We benchmark NVIDIA A100 80 GB (PCIe) vs NVIDIA H100 NVL (PCIe) vs NVIDIA RTX 6000 Ada GPUs and compare AI performance (deep learning training; FP16, FP32, PyTorch, TensorFlow), 3d rendering, Cryo-EM performance in the most popular apps (Octane, VRay, Redshift, Blender, Luxmark, Unreal Engine, Relion Cryo-EM).

Our benchmarks will help you decide which GPU (NVIDIA RTX 4090/4080, H100 Hopper, H200, A100, RTX 6000 Ada, A6000, A5000, or RTX 6000 ADA Lovelace) is the best GPU for your needs. We provide an in-depth analysis of the AI performance of each graphic card's performance so you can make the most informed decision possible. We offer deep learning and 3d rendering benchmarks that will help you get the most out of your hardware.


Looking for a GPU workstation or server for AI/ML, design, rendering, simulation or molecular dynamics?
Explore BIZON AI workstations or GPU servers.
Contact us today or explore our various customizable AI solutions.


Featured GPU benchmarks:

Benchmarks

Deep Learning GPU Benchmarks 2024–2025 [Updated]

As of April 2025

Resnet50 (FP16)

1 GPU
NVIDIA A100 80 GB (PCIe)
2535 points
NVIDIA H100 NVL (PCIe)
3042 points
NVIDIA RTX 6000 Ada
1800 points
4 GPU
NVIDIA A100 80 GB (PCIe)
9366 points
NVIDIA H100 NVL (PCIe)
11989 points
NVIDIA RTX 6000 Ada
6369 points
8 GPU
NVIDIA A100 80 GB (PCIe)
21479 points
NVIDIA H100 NVL (PCIe)
30070 points
NVIDIA RTX 6000 Ada
16968 points
higher is better

Resnet50 (FP32)

1 GPU
NVIDIA A100 80 GB (PCIe)
1144 points
NVIDIA H100 NVL (PCIe)
1350 points
NVIDIA RTX 6000 Ada
709 points
4 GPU
NVIDIA A100 80 GB (PCIe)
4273 points
NVIDIA H100 NVL (PCIe)
5513 points
NVIDIA RTX 6000 Ada
2692 points
8 GPU
NVIDIA A100 80 GB (PCIe)
9752 points
NVIDIA H100 NVL (PCIe)
14725 points
NVIDIA RTX 6000 Ada
7607 points
higher is better

Resnet152 (FP16)

1 GPU
NVIDIA A100 80 GB (PCIe)
1027 points
NVIDIA H100 NVL (PCIe)
1232 points
NVIDIA RTX 6000 Ada
729 points
4 GPU
NVIDIA A100 80 GB (PCIe)
3795 points
NVIDIA H100 NVL (PCIe)
4858 points
NVIDIA RTX 6000 Ada
2581 points
8 GPU
NVIDIA A100 80 GB (PCIe)
8865 points
NVIDIA H100 NVL (PCIe)
12411 points
NVIDIA RTX 6000 Ada
7004 points
higher is better

Resnet152 (FP32)

1 GPU
NVIDIA A100 80 GB (PCIe)
441 points
NVIDIA H100 NVL (PCIe)
520 points
NVIDIA RTX 6000 Ada
273 points
4 GPU
NVIDIA A100 80 GB (PCIe)
1646 points
NVIDIA H100 NVL (PCIe)
2124 points
NVIDIA RTX 6000 Ada
1037 points
8 GPU
NVIDIA A100 80 GB (PCIe)
3941 points
NVIDIA H100 NVL (PCIe)
5950 points
NVIDIA RTX 6000 Ada
3074 points
higher is better

Inception V3 (FP16)

1 GPU
NVIDIA A100 80 GB (PCIe)
1529 points
NVIDIA H100 NVL (PCIe)
1835 points
NVIDIA RTX 6000 Ada
1086 points
4 GPU
NVIDIA A100 80 GB (PCIe)
5650 points
NVIDIA H100 NVL (PCIe)
7232 points
NVIDIA RTX 6000 Ada
3842 points
8 GPU
NVIDIA A100 80 GB (PCIe)
11305 points
NVIDIA H100 NVL (PCIe)
15827 points
NVIDIA RTX 6000 Ada
8931 points
higher is better

Inception V3 (FP32)

1 GPU
NVIDIA A100 80 GB (PCIe)
724 points
NVIDIA H100 NVL (PCIe)
854 points
NVIDIA RTX 6000 Ada
449 points
4 GPU
NVIDIA A100 80 GB (PCIe)
2703 points
NVIDIA H100 NVL (PCIe)
3487 points
NVIDIA RTX 6000 Ada
1703 points
8 GPU
NVIDIA A100 80 GB (PCIe)
6514 points
NVIDIA H100 NVL (PCIe)
9837 points
NVIDIA RTX 6000 Ada
5081 points
higher is better

Inception V4 (FP16)

1 GPU
NVIDIA A100 80 GB (PCIe)
707 points
NVIDIA H100 NVL (PCIe)
848 points
NVIDIA RTX 6000 Ada
502 points
4 GPU
NVIDIA A100 80 GB (PCIe)
2612 points
NVIDIA H100 NVL (PCIe)
3343 points
NVIDIA RTX 6000 Ada
1776 points
8 GPU
NVIDIA A100 80 GB (PCIe)
4871 points
NVIDIA H100 NVL (PCIe)
6819 points
NVIDIA RTX 6000 Ada
3848 points
higher is better

Inception V4 (FP32)

1 GPU
NVIDIA A100 80 GB (PCIe)
322 points
NVIDIA H100 NVL (PCIe)
380 points
NVIDIA RTX 6000 Ada
200 points
4 GPU
NVIDIA A100 80 GB (PCIe)
1202 points
NVIDIA H100 NVL (PCIe)
1551 points
NVIDIA RTX 6000 Ada
757 points
8 GPU
NVIDIA A100 80 GB (PCIe)
2977 points
NVIDIA H100 NVL (PCIe)
4496 points
NVIDIA RTX 6000 Ada
2322 points
higher is better

VGG16 (FP16)

1 GPU
NVIDIA A100 80 GB (PCIe)
904 points
NVIDIA H100 NVL (PCIe)
1085 points
NVIDIA RTX 6000 Ada
642 points
4 GPU
NVIDIA A100 80 GB (PCIe)
3341 points
NVIDIA H100 NVL (PCIe)
4276 points
NVIDIA RTX 6000 Ada
2272 points
8 GPU
NVIDIA A100 80 GB (PCIe)
11363 points
NVIDIA H100 NVL (PCIe)
15908 points
NVIDIA RTX 6000 Ada
8977 points
higher is better

VGG16 (FP32)

1 GPU
NVIDIA A100 80 GB (PCIe)
658 points
NVIDIA H100 NVL (PCIe)
776 points
NVIDIA RTX 6000 Ada
408 points
4 GPU
NVIDIA A100 80 GB (PCIe)
2458 points
NVIDIA H100 NVL (PCIe)
3171 points
NVIDIA RTX 6000 Ada
1549 points
8 GPU
NVIDIA A100 80 GB (PCIe)
5803 points
NVIDIA H100 NVL (PCIe)
8762 points
NVIDIA RTX 6000 Ada
4526 points
higher is better

3D, GPU Rendering Benchmarks 2024–2025 [Updated]

As of April 2025

V-Ray

1 GPU
NVIDIA A100 80 GB (PCIe)
n/a
NVIDIA H100 NVL (PCIe)
n/a
NVIDIA RTX 6000 Ada
4798 points
higher is better

Octane

1 GPU
NVIDIA A100 80 GB (PCIe)
n/a
NVIDIA H100 NVL (PCIe)
n/a
NVIDIA RTX 6000 Ada
1140 points
higher is better

Redshift

1 GPU
NVIDIA A100 80 GB (PCIe)
n/a
NVIDIA H100 NVL (PCIe)
n/a
NVIDIA RTX 6000 Ada
1.27 minutes
lower is better

Blender

1 GPU
NVIDIA A100 80 GB (PCIe)
3935.71 score
NVIDIA H100 NVL (PCIe)
5069.86 score
NVIDIA RTX 6000 Ada
11864.76 score
higher is better

Unreal Engine

1 GPU
NVIDIA A100 80 GB (PCIe)
n/a
NVIDIA H100 NVL (PCIe)
n/a
NVIDIA RTX 6000 Ada
78.5 FPS
higher is better

Llama3 70B Inference Benchmark 2024–2025 [Updated]

As of April 2025

Eval rate

1 GPU
NVIDIA A100 80 GB (PCIe)
25.35 tokens/s
NVIDIA H100 NVL (PCIe)
n/a
NVIDIA RTX 6000 Ada
18.06 tokens/s
higher is better

Technical Specifications

Board Design

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
Length11 in / 267 mm11 in / 268 mm11 in / 267 mm
OutputsNo outputsNo outputs4x DisplayPort
Power Connectors8-pin EPS8-pin EPS1x 16-pin
Slot widthDual-slotDual-slotDual-slot
TDP250 W700 W300 W

Clock Speeds

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
Boost Clock1410 MHz1837 MHz2505 MHz
GPU Clock1065 MHz1665 MHz915 MHz
Memory Clock3200 MHz5300 MHz20000 MHz

Graphics Card

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
Bus InterfacePCIe 4.0 x16PCIe 5.0 x16PCIe 4.0 x16
GenerationTesla (Axx)Server Hopper (Hxx)Quadro Ada (x000A)

Graphics Features

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
OpenCL333
CUDA898.9
DirectX--12 Ultimate (12_2)
OpenGL--4.6
Shader Model--6.7

Graphics Processor

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
ArchitectureAmpereHopperAda Lovelace
Die Size826 mm2814 mm2608 mm2
GPU NameGA100GH100AD102
Process Size7 nm5 nm5 nm
Transistors54200 million80000 million76300 million

Memory

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
Bandwidth2039 GB/s3360 GB/s960 GB/s
Memory Bus5120 bit5120 bit384 bit
Memory Size80 GB96 GB48 GB
Memory TypeHBM2eHBM3GDDR6

Render Config

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
ROPs16024192
Shading Units/ CUDA Cores69121689618176
TMUs432528568
Tensor Cores432528568
RT Cores--142

Theoretical Performance

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
FP16 (half) performance77.97 TFLOPS248.3 TFLOPS91.06 TFLOPS
FP32 (float) performance19.49 TFLOPS62.08 TFLOPS91.06 TFLOPS
FP64 (double) performance9746 GFLOPS31040 GFLOPS1423 GFLOPS
Pixel Rate225.6 GPixel/s44.09 GPixel/s481 GPixel/s
Texture Rate609.1 GTexel/s969.9 GTexel/s1423 GTexel/s

Price

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
Release DateJun 28th, 2021Mar 21st, 2023Jan 20th, 2023
MSRP--$6,799.00

Test bench configuration

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
HardwareBIZON X5000 More detailsBIZON X5000 More detailsBIZON X5500 More details
Software3D Rendering:
Nvidia Driver: 461.09
VRay Benchmark: 5
Octane Benchmark: 2020.1.5
Redshift Benchmark: 3.0.28 Demo
Blender: 2.90
Luxmark: 3.1
3D Rendering:
VRay Benchmark: 5
Octane Benchmark: 2020.1.5
Redshift Benchmark: 3.0.28 Demo
Blender: 2.90
Luxmark: 3.1
3D Rendering:
Nvidia Driver:
VRay Benchmark:
Octane Benchmark:
Redshift Benchmark:
Blender:
Luxmark:

Recommended hardware

NVIDIA A100 80 GB (PCIe)NVIDIA H100 NVL (PCIe)NVIDIA RTX 6000 Ada
Best GPU workstationsBIZON X5500BIZON X5500BIZON X5500
Best NVIDIA GPU serversBIZON X7000BIZON X7000BIZON X7000
Need Help? We're here to help.

Unsure what to get? Have technical questions?
Contact us and we'll help you design a custom system which will meet your needs.

Explore Products