NVIDIA GeForce RTX 4090 Ti vs NVIDIA GeForce RTX 4090

Comparative analysis of NVIDIA GeForce RTX 4090 Ti and NVIDIA GeForce RTX 4090 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G2D Mark, PassMark - G3D Mark, 3DMark Fire Strike - Graphics Score, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), Geekbench - OpenCL, CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s).

NVIDIA GeForce RTX 4090 Ti

NVIDIA GeForce RTX 4090

Differences

Reasons to consider the NVIDIA GeForce RTX 4090 Ti

Videocard is newer: launch date 2 year(s) 1 month(s) later
Around 5% higher core clock speed: 2355 MHz vs 2235 MHz
Around 4% higher boost clock speed: 2625 MHz vs 2520 MHz
Around 16% higher texture fill rate: 1,491 GTexel/s vs 1,290 GTexel/s
Around 11% higher pipelines: 18176 vs 16384
2x more maximum memory size: 48 GB vs 24 GB
Around 14% higher memory clock speed: 1500 MHz, 24 Gbps effective vs 1313 MHz, 21 Gbps effective

Launch date	2023 vs 20 Sep 2022
Core clock speed	2355 MHz vs 2235 MHz
Boost clock speed	2625 MHz vs 2520 MHz
Texture fill rate	1,491 GTexel/s vs 1,290 GTexel/s
Pipelines	18176 vs 16384
Maximum memory size	48 GB vs 24 GB
Memory clock speed	1500 MHz, 24 Gbps effective vs 1313 MHz, 21 Gbps effective

Reasons to consider the NVIDIA GeForce RTX 4090

Around 78% lower typical power consumption: 450 Watt vs 800 Watt

Thermal Design Power (TDP)	450 Watt vs 800 Watt

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 4090 Ti
GPU 2: NVIDIA GeForce RTX 4090

Name	NVIDIA GeForce RTX 4090 Ti	NVIDIA GeForce RTX 4090
PassMark - G2D Mark		1295
PassMark - G3D Mark		38582
3DMark Fire Strike - Graphics Score		36466
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		472.899
CompuBench 1.5 Desktop - T-Rex (Frames/s)		95.851
CompuBench 1.5 Desktop - Video Composition (Frames/s)		221.169
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		4429.59
Geekbench - OpenCL		317368
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		0

Compare specifications (specs)

	NVIDIA GeForce RTX 4090 Ti	NVIDIA GeForce RTX 4090
Essentials
Architecture	Ada Lovelace	Ada Lovelace
Code name	AD102	AD102
Launch date	2023	20 Sep 2022
Place in performance rating	not rated	8
Technical info
Boost clock speed	2625 MHz	2520 MHz
Core clock speed	2355 MHz	2235 MHz
Manufacturing process technology	4 nm	4 nm
Peak Double Precision (FP64) Performance	1,491 GFLOPS (1:64)	1,290 GFLOPS (1:64)
Peak Half Precision (FP16) Performance	95.42 TFLOPS (1:1)	82.58 TFLOPS (1:1)
Peak Single Precision (FP32) Performance	95.42 TFLOPS	82.58 TFLOPS
Pipelines	18176	16384
Pixel fill rate	504.0 GPixel/s	443.5 GPixel/s
Texture fill rate	1,491 GTexel/s	1,290 GTexel/s
Thermal Design Power (TDP)	800 Watt	450 Watt
Transistor count	76300 million	76300 million
Video outputs and ports
Display Connectors	1x HDMI 2.1, 3x DisplayPort 1.4a	1x HDMI 2.1, 3x DisplayPort 1.4a
Compatibility, dimensions and requirements
Form factor	Triple-slot	Triple-slot
Height	61 mm, 2.4 inches	61 mm, 2.4 inches
Interface	PCIe 4.0 x16	PCIe 4.0 x16
Length	336 mm, 13.2 inches	304 mm, 12 inches
Recommended system power (PSU)	1200 Watt	850 Watt
Supplementary power connectors	2x 16-pin	1x 16-pin
Width	140 mm, 5.5 inches	137 mm, 5.4 inches
API support
DirectX	12 Ultimate (12_2)	12 Ultimate (12_2)
OpenCL	3.0	3.0
OpenGL	4.6	4.6
Shader Model	6.7	6.7
Vulkan
Memory
Maximum RAM amount	48 GB	24 GB
Memory bandwidth	1,152 GB/s	1,008 GB/s
Memory bus width	384 bit	384 bit
Memory clock speed	1500 MHz, 24 Gbps effective	1313 MHz, 21 Gbps effective
Memory type	GDDR6X	GDDR6X