NVIDIA RTX A6000 vs NVIDIA A100 40 GB (PCIe) vs NVIDIA H100 (PCIe) vs NVIDIA RTX 4090
NVIDIA RTX 2080 Ti
NVIDIA Titan RTX
NVIDIA Quadro RTX 6000
NVIDIA Quadro RTX 8000
NVIDIA GTX 1080 Ti
NVIDIA Titan V
NVIDIA Tesla V100
NVIDIA GTX 780
NVIDIA GTX 780 Ti
NVIDIA GTX 960
NVIDIA GTX 980
NVIDIA GTX 980 Ti
NVIDIA GTX 1050
NVIDIA GTX 1050 Ti
NVIDIA GTX 1060
NVIDIA GTX 1070
NVIDIA GTX 1070 Ti
NVIDIA GTX 1080
NVIDIA GTX 1650
NVIDIA GTX 1660
NVIDIA GTX 1660 Ti
NVIDIA RTX 2060
NVIDIA RTX 2060 Super
NVIDIA RTX 2070
NVIDIA RTX 2070 Super
NVIDIA RTX 2080
NVIDIA RTX 2080 Super
NVIDIA Titan Xp
NVIDIA Quadro M6000
NVIDIA Quadro P1000
NVIDIA Quadro P2000
NVIDIA Quadro P4000
NVIDIA Quadro P5000
NVIDIA Quadro P6000
NVIDIA Quadro GP100
NVIDIA Quadro GV100
NVIDIA Quadro RTX 4000
NVIDIA Quadro RTX 5000
NVIDIA RTX 3070
NVIDIA RTX 3080
NVIDIA RTX 3090
NVIDIA RTX A6000
NVIDIA RTX 3060
NVIDIA RTX 3060 Ti
NVIDIA A100 40 GB (PCIe)
NVIDIA A40
NVIDIA A10
NVIDIA A16
NVIDIA A30
NVIDIA RTX A4000
NVIDIA RTX A5000
NVIDIA RTX 3070 Ti
NVIDIA RTX 3080 Ti
NVIDIA A100 80 GB (PCIe)
NVIDIA A100 80 GB (SXM4)
NVIDIA RTX A4500
NVIDIA T400
NVIDIA T600
NVIDIA T1000
NVIDIA RTX A5500
NVIDIA RTX A2000
NVIDIA H100 (PCIe)
NVIDIA H100 (SXM5)
NVIDIA H100 CNX
NVIDIA RTX 3090 Ti
NVIDIA RTX 4090
NVIDIA RTX 4080
NVIDIA RTX 4070 Ti
NVIDIA RTX 6000 Ada
NVIDIA L40
NVIDIA RTX 4090 Ti (Unreleased)
NVIDIA RTX 4000 SFF Ada
NVIDIA RTX 4070
NVIDIA L40s
NVIDIA RTX 4000 Ada
NVIDIA RTX 4500 Ada
NVIDIA RTX 5000 Ada
NVIDIA A800 40 GB (PCIe)
NVIDIA A800 40 GB Active
NVIDIA H200 (SXM5)
NVIDIA GH200
NVIDIA L4
NVIDIA B200 (SXM)
NVIDIA RTX 5090 (Unreleased)
NVIDIA H200 (PCIe)
NVIDIA RTX 5080 (Unreleased)
X
+
VS
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 these 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:
Deep Learning GPU Benchmarks 2023–2024 [Updated]
Resnet50 (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
2179
4 GPU
NVIDIA A100 40 GB (PCIe)
8561
8 GPU
NVIDIA A100 40 GB (PCIe)
16797
Resnet50 (FP16 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Resnet50 (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
1001
4 GPU
NVIDIA A100 40 GB (PCIe)
3849
8 GPU
NVIDIA A100 40 GB (PCIe)
7557
Resnet50 (FP32 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Resnet152 (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
930
4 GPU
NVIDIA A100 40 GB (PCIe)
3557
8 GPU
NVIDIA A100 40 GB (PCIe)
6809
Resnet152 (FP16 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Resnet152 (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
409
4 GPU
NVIDIA A100 40 GB (PCIe)
1498
8 GPU
NVIDIA A100 40 GB (PCIe)
2851
Resnet152 (FP32 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Inception V3 (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
1283
4 GPU
NVIDIA A100 40 GB (PCIe)
5218
8 GPU
NVIDIA A100 40 GB (PCIe)
10122
Inception V3 (FP16 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Inception V3 (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
658
4 GPU
NVIDIA A100 40 GB (PCIe)
2568
8 GPU
NVIDIA A100 40 GB (PCIe)
5058
Inception V3 (FP32 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Inception V4 (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
616
4 GPU
NVIDIA A100 40 GB (PCIe)
2377
8 GPU
NVIDIA A100 40 GB (PCIe)
4532
Inception V4 (FP16 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Inception V4 (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
290
4 GPU
NVIDIA A100 40 GB (PCIe)
1031
8 GPU
NVIDIA A100 40 GB (PCIe)
1950
Inception V4 (FP32 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
VGG16 (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
1249
4 GPU
NVIDIA A100 40 GB (PCIe)
4989
8 GPU
NVIDIA A100 40 GB (PCIe)
10733
VGG16 (FP16 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
VGG16 (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
529
4 GPU
NVIDIA A100 40 GB (PCIe)
2215
8 GPU
NVIDIA A100 40 GB (PCIe)
4278
VGG16 (FP32 XLA)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Googlenet (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Googlenet (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
3D, GPU Rendering Benchmarks 2023–2024 [Updated]
V-Ray
1 GPU
NVIDIA A100 40 GB (PCIe)
1555
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Octane
1 GPU
NVIDIA A100 40 GB (PCIe)
498
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Redshift
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Blender
1 GPU
NVIDIA A100 40 GB (PCIe)
3788
NVIDIA H100 (PCIe)
5069.86
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Luxmark
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Unreal Engine
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
RELION Cryo-EM Benchmarks 2023-2024 [Updated]
Total run time
1 GPU
NVIDIA A100 40 GB (PCIe)
178.9
4 GPU
NVIDIA A100 40 GB (PCIe)
50.3
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
BERT LARGE Training, Inference Benchmark 2023-2024 [Updated]
Training Time (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Performance (FP16)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Training Time (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Performance (FP32)
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
8 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Llama3 70B Inference Benchmark 2024 [Updated]
Eval rate
1 GPU
NVIDIA A100 40 GB (PCIe)
n/a
2 GPU
NVIDIA A100 40 GB (PCIe)
n/a
4 GPU
NVIDIA A100 40 GB (PCIe)
n/a
Board Design
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
Length
267 mm
267 mm
268 mm
336 mm
Outputs
4x DisplayPort
No outputs
No outputs
1x HDMI, 3x DisplayPort
Power Connectors
8-pin EPS
8-pin EPS
1x 16-pin
1x 16-pin
Slot width
Dual-slot
Dual-slot
Dual-slot
Triple-slot
TDP
300 W
250 W
350 W
450 W
Clock Speeds
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
Boost Clock
1860 MHz
1410 MHz
1755 MHz
2520 MHz
GPU Clock
1455 MHz
765 MHz
1095 MHz
2235 MHz
Memory Clock
16000 MHz
2400 MHz
1593 MHz
21200 MHz
Graphics Card
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
PCIe 5.0 x16
PCIe 4.0 x16
Generation
Quadro (Ax000)
Tesla (Axx)
Tesla Hopper (Hxx)
GeForce 40
Graphics Features
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenCL
3.0
2.0
3.0
3.0
OpenGL
4.6
4.6
Shader Model
6.6
6.7
CUDA
8.6
8.0
9.0
8.9
Graphics Processor
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
Architecture
Ampere
Ampere
Hopper
Ada Lovelace
Die Size
628 mm2
826 mm2
814 mm2
608 mm2
GPU Name
GA102
GA100
GH100
AD102-300-A1
Process Size
8 nm
7 nm
4 nm
5 nm
Transistors
28300 million
54200 million
80000 million
76300 million
Memory
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
Bandwidth
768 GB/s
1555 GB/s
2039 GB/s
1018 GB/s
Memory Bus
384 bit
5120 bit
5120 bit
384 bit
Memory Size
48 GB
40 GB
80 GB
24 GB
Memory Type
GDDR6
HBM2e
HBM2e
GDDR6X
Render Config
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
ROPs
112
160
24
192
RT Cores
84
128
Shading Units/ CUDA Cores
10752
6912
14592
16384
TMUs
336
432
456
512
Tensor Cores
336
432
456
512
Theoretical Performance
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
FP16 (half) performance
38.71 TFLOPS
77.97 TFLOPS
204.9 TFLOPS
82.58 TFLOPS
FP32 (float) performance
38.71 TFLOPS
19.49 TFLOPS
51.22 TFLOPS
82.58 TFLOPS
FP64 (double) performance
1210 GFLOPS
9746 GFLOPS
25610 GFLOPS
1290 GFLOPS
Pixel Rate
201.6 GPixel/s
225.6 GPixel/s
42.12 GPixel/s
483.8 GPixel/s
Texture Rate
604.8 GTexel/s
609.1 GTexel/s
800.3 GTexel/s
1290 GTexel/s
Price
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
MSRP
4649 $
$
$
1599 $
Release Date
Oct 5th, 2020
Jun 22nd, 2020
Mar 22nd, 2022
Oct 12th, 2022
Test bench configuration
NVIDIA RTX A6000
NVIDIA A100 40 GB (PCIe)
NVIDIA H100 (PCIe)
NVIDIA RTX 4090
Hardware
BIZON X5000 More details
BIZON X5000 More details
BIZON X5000 More details
BIZON X5500 More details
Software
3D Rendering:
Nvidia Driver: 461.40
VRay Benchmark: 5
Octane Benchmark: 2020.1.5
Redshift Benchmark: 3.0.28 Demo
Blender: 2.90
Luxmark: 3.1
3D 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:
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:
Nvidia Driver:
VRay Benchmark:
Octane Benchmark:
Redshift Benchmark:
Blender:
Luxmark: