1-888-577-6775 sales@bizon-tech.com
  1. Home
  2. Compare

GPU Benchmarks NVIDIA RTX 4090 vs. NVIDIA RTX 4090 Ti (Unreleased)

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 RTX 4090 vs NVIDIA RTX 4090 Ti (Unreleased) 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 June 2025

Resnet50 (FP16)

1 GPU
NVIDIA RTX 4090
1720 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
4 GPU
NVIDIA RTX 4090
5934 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

Resnet50 (FP32)

1 GPU
NVIDIA RTX 4090
927 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
4 GPU
NVIDIA RTX 4090
1715 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

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

As of June 2025

V-Ray

1 GPU
NVIDIA RTX 4090
5556 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

Octane

1 GPU
NVIDIA RTX 4090
1445 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

Redshift

1 GPU
NVIDIA RTX 4090
1.16 minutes
NVIDIA RTX 4090 Ti (Unreleased)
n/a
lower is better

Blender

1 GPU
NVIDIA RTX 4090
12123.96 score
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

Luxmark

1 GPU
NVIDIA RTX 4090
158815 points
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

Unreal Engine

1 GPU
NVIDIA RTX 4090
92.1 FPS
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

RELION Cryo-EM Benchmarks 2024-2025 [Updated]↑

As of June 2025

Total run time

1 GPU
NVIDIA RTX 4090
105.2 Min
NVIDIA RTX 4090 Ti (Unreleased)
n/a
4 GPU
NVIDIA RTX 4090
53.2 Min
NVIDIA RTX 4090 Ti (Unreleased)
n/a
lower is better

Llama3 70B Inference Benchmark 2024–2025 [Updated]↑

As of June 2025

Eval rate

1 GPU
NVIDIA RTX 4090
9.95 tokens/s
NVIDIA RTX 4090 Ti (Unreleased)
n/a
2 GPU
NVIDIA RTX 4090
19.99 tokens/s
NVIDIA RTX 4090 Ti (Unreleased)
n/a
higher is better

Technical Specifications

Board Design

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
Length13 in / 336 mm13 in / 336 mm-
Outputs1x HDMI, 3x DisplayPort1x HDMI, 3x DisplayPort-
Power Connectors1x 16-pin2x 16-pin
Slot widthTriple-slotTriple-slot-
TDP450 W800 W350 W (78%)

Clock Speeds

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
Boost Clock2520 MHz2625 MHz105 MHz (4%)
GPU Clock2235 MHz2355 MHz120 MHz (5%)
Memory Clock21200 MHz24000 MHz2800 MHz (13%)

Graphics Card

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
Bus InterfacePCIe 4.0 x16PCIe 4.0 x16-
GenerationGeForce 40GeForce 40-

Graphics Features

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
DirectX12 Ultimate (12_2)12 Ultimate (12_2)-
OpenCL33-
OpenGL4.64.6-
Shader Model6.76.7-
CUDA8.98.9-

Graphics Processor

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
ArchitectureAda LovelaceAda Lovelace-
Die Size608 mm2608 mm2-
GPU NameAD102-300-A1AD102-450-A1
Process Size5 nm5 nm-
Transistors76300 million76300 million-

Memory

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
Bandwidth1018 GB/s1152 GB/s134 GB/s (13%)
Memory Bus384 bit384 bit-
Memory Size24 GB48 GB24 GB (100%)
Memory TypeGDDR6XGDDR6X-

Render Config

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
ROPs192192-
RT Cores12814214 (11%)
Shading Units/ CUDA Cores16384181761792 (11%)
TMUs51256856 (11%)
Tensor Cores51256856 (11%)

Theoretical Performance

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
FP16 (half) performance82.58 TFLOPS95.42 TFLOPS12.84 TFLOPS (16%)
FP32 (float) performance82.58 TFLOPS95.42 TFLOPS12.84 TFLOPS (16%)
FP64 (double) performance1290 GFLOPS1491 GFLOPS201 GFLOPS (16%)
Pixel Rate483.8 GPixel/s504 GPixel/s20.2 GPixel/s (4%)
Texture Rate1290 GTexel/s1491 GTexel/s201 GTexel/s (16%)

Price

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
MSRP$1,599.00-
Release DateOct 12th, 20222023

Test bench configuration

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
HardwareBIZON X5500 More detailsBIZON X5500 More details-
Software3D Rendering:
Nvidia Driver:
VRay Benchmark:
Octane Benchmark:
Redshift Benchmark:
Blender:
Luxmark:		3D Rendering:
Nvidia Driver:
VRay Benchmark:
Octane Benchmark:
Redshift Benchmark:
Blender:
Luxmark:		-

Recommended hardware

NVIDIA RTX 4090NVIDIA RTX 4090 Ti (Unreleased)Difference
Best GPU workstationsBIZON X5500BIZON X5500-
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