Select processor 1
Select processor 2
NVIDIA GeForce RTX 3090 Ti
NVIDIA GeForce RTX 4060

NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4060. Specifications, performance, tests

User rating
star star star star star
Released
Q1/2022
NVIDIA GeForce RTX 3090 Ti
NVIDIA GeForce RTX 3090 Ti
Released
Q3/2023
User rating
star star star star star
NVIDIA GeForce RTX 4060
NVIDIA GeForce RTX 4060

What's the best choice NVIDIA GeForce RTX 3090 Ti or NVIDIA GeForce RTX 4060? Which graphics card is faster?

Compare the available specifications of these models.

NVIDIA GeForce RTX 3090 Ti has a base frequency of 1.56 GHz. Memory size 24 GB. Memory type GDDR6X. Released in Q1/2022.

NVIDIA GeForce RTX 4060 has a base frequency of 1.83 GHz. Memory size 8 GB. Memory type GDDR6. Released in Q3/2023.

Differences

  • More memory

    200% more memory

    24 GB left arrow 8 GB

Positions in all rankings

Common positions NVIDIA GeForce RTX 3090 Ti GPU in popular benchmarks, for comparison with other models.

  • Passmark Performance Test GPU
    1 place
  • Higher clock speed

    Around 17% better clock speed

    1.83 GHz left arrow 1.56 GHz

Positions in all rankings

Common positions NVIDIA GeForce RTX 4060 GPU in popular benchmarks, for comparison with other models.

  • FP32 Performance (Single-precision TFLOPS)
    832 place

Specifications

Technical data
NVIDIA GeForce RTX 3090 Ti NVIDIA GeForce RTX 3090 Ti
NVIDIA GeForce RTX 4060 NVIDIA GeForce RTX 4060
General info

Comparison of basic technical data of graphics cards NVIDIA GeForce RTX 3090 Ti and NVIDIA GeForce RTX 4060, chip, information processing units.

  • Architecture
    Ampere left arrow Ada Lovelace
  • Based on
    GA102 left arrow NVIDIA GeForce RTX 4060
  • CUDA Cores
    10752 left arrow 3072
  • GPU Chip
    GA102-350-A1 left arrow AD107
  • L1 Cache
    128 KB left arrow -
  • L2 Cache
    6 MB left arrow -
  • Render Output Units
    112 left arrow 32
  • Shader
    10752 left arrow 3072
  • Texture Units
    336 left arrow 96
  • RT Cores
    - left arrow 24
  • Streaming Multiprocessors
    - left arrow 24
Memory settings

Video memory capacity, type, bus width and bandwidth describe different properties. These values alone do not determine graphics performance.

  • Memory Bandwidth
    1,008 GB/s left arrow 272 GB/s
  • Memory Bus
    384 bit left arrow 128 bit
  • Memory Size
    24 GB left arrow 8 GB
  • Memory Speed (legacy frequency label)
    1300 MHz left arrow -
  • Memory Type
    GDDR6X left arrow GDDR6
  • Memory Clock
    - left arrow 2125 MHz
  • Memory Data Rate
    - left arrow 17 Gbps
Clock frequency

Published GPU clock frequencies describe different operating modes. Clock speed alone does not determine graphics performance.

  • Base Clock
    1560 MHz left arrow 1830 MHz
  • Boost Clock
    1860 MHz left arrow 2460 MHz
  • Overclocking
    No left arrow Yes
  • Game Clock
    - left arrow -
Thermal Management

Graphics card power limits and recommended system power supply describe different specifications.

  • Graphics Card Power
    450 W left arrow -
  • Maximum GPU Temperature
    92 °C left arrow 90 °C
  • System Power Supply
    850 W (System power requirement) left arrow 550 W (System power requirement)
  • TDP
    450 W left arrow 115 W
  • Maximum Junction Temperature
    - left arrow 90 °C
  • TDP (up)
    - left arrow -
  • Total Graphics Power
    - left arrow 115 W
Cooler & Fans type

Types and sizes of coolers for graphics card cooling system NVIDIA GeForce RTX 3090 Ti and NVIDIA GeForce RTX 4060.

  • Cooler-Type
    - left arrow Air cooling
  • Fan-Type
    - left arrow -
  • Fan 1
    - left arrow -
  • Fan 2
    - left arrow -
  • Noise (Idle)
    - left arrow 0 dB / Silent
  • Noise (Load)
    - left arrow -
Interfaces

Connectivity and connections.

  • DisplayPort Ports
    3 × DisplayPort 1.4a left arrow 3 × DisplayPort
  • HDCP Version
    2.3 left arrow 2.3
  • HDMI Ports
    1 × HDMI 2.1 left arrow 1 × HDMI 2.1a
  • Max. Displays
    4 left arrow 4
  • Other Display Outputs (unparsed)
    HDMI left arrow HDMI
  • PCIe Interface
    PCIe 4.0 x16 left arrow PCIe 4.0 x8
  • Power Connectors
    3x PCIe 8-pin cables (adapter in box) OR 450W or greater PCIe Gen 5 cable left arrow 1x PCIe 8-pin cables (adapter in box) OR 300 W or greater PCIe Gen 5 cable. Certain manufacturer models may use 1x PCIe 6-pin cable or 1x PCIe 8-pin cable
  • DVI Ports
    - left arrow -
  • USB-C Ports
    - left arrow -
  • VGA Ports
    - left arrow -
Technical data

Technical data that is used to its full potential in computer games.

  • DirectX
    12_2 left arrow 12_2 (Ultimate)
  • Max. resolution
    7680 × 4320 left arrow 7680 × 4320
  • OpenCL
    3.0 left arrow -
  • OpenGL
    4.6 left arrow -
  • Shader Model
    6.6 left arrow -
  • Vulkan
    1.3 left arrow -
  • DLSS / FSR
    - left arrow Yes
  • LED
    - left arrow No LED lighting
  • Raytracing
    - left arrow Yes
Supported Video Codecs

Built-in support for video and image compression standards.

  • AV1
    - left arrow Decode / Encode
  • h264
    - left arrow Decode / Encode
  • h265 / HEVC
    - left arrow Decode / Encode
  • VP8
    - left arrow Decode
  • VP9
    - left arrow Decode
Dimensions

The difference in size, weight and slot of the compared devices

  • Height
    - left arrow -
  • Length
    - left arrow -
  • Slot Size
    - left arrow -
  • Weight
    - left arrow -
  • Width
    - left arrow -
More information

Comparison of interfaces and release dates for GPU NVIDIA GeForce RTX 4060 and NVIDIA GeForce RTX 3090 Ti.

  • Manufacturer specification scope
    NVIDIA Founders Edition/reference design. Clock specifications apply to gaming use. AIB shipping specifications and complete-system power needs may differ. left arrow NVIDIA Founders Edition/reference design. Clock specifications apply to gaming use. AIB shipping specifications and complete-system power needs may differ.
  • Process Technology
    8 nm left arrow 4 nm
  • Documents
    - left arrow data sheet
  • Launch Price (historical)
    - left arrow 299 $
  • Part Number
    - left arrow -
  • Release date
    - left arrow Q3/2023
Theoretical Performance

  • FP16 (theoretical)
    40 TFLOPS left arrow -
  • FP32 (theoretical)
    40 TFLOPS left arrow -
  • FP64 (theoretical)
    0.625 TFLOPS left arrow -
  • Pixel Rate
    208.3 GPixel/s left arrow -
  • Texture Rate
    625.0 GTexel/s left arrow -

Benchmarks

Performance tests GPUs

Shared tests with results for both models: 15

Blender Cycles

Each row uses one Blender version, operating system and compute backend.

Test and settingsNVIDIA GeForce RTX 3090 Ti NVIDIA GeForce RTX 4060Result difference¹
Blender 5.2.0 / OPTIX / Windows 5257.100902 samples/min Submissions: 13 2959.686531 samples/min Submissions: 64 -43.7 %
Blender 5.1.1 / OPTIX / Linux 5601.471369 samples/min Submissions: 7 3185.644189 samples/min Submissions: 17 -43.1 %
Blender 5.1.1 / OPTIX / Windows 5459.157697 samples/min Submissions: 5 2988.836344 samples/min Submissions: 53 -45.3 %
Blender 4.5.0 / OPTIX / Linux 5309.43807 samples/min Submissions: 24 3224.628872 samples/min Submissions: 158 -39.3 %
Blender 4.5.0 / OPTIX / Windows 5585.151795 samples/min Submissions: 115 3125.069793 samples/min Submissions: 281 -44.0 %
Blender 4.4.0 / OPTIX / Linux 4979.851473 samples/min Submissions: 8 3238.448821 samples/min Submissions: 32 -35.0 %
Blender 4.4.0 / OPTIX / Windows 5700.575741 samples/min Submissions: 51 3117.445682 samples/min Submissions: 248 -45.3 %
Blender 4.3.0 / OPTIX / Linux 5840.23445 samples/min Submissions: 8 3153.326645 samples/min Submissions: 33 -46.0 %
Blender 4.3.0 / OPTIX / Windows 5490.159484 samples/min Submissions: 35 3044.770801 samples/min Submissions: 286 -44.5 %
Blender 4.2.0 / OPTIX / Linux 5972.585335 samples/min Submissions: 15 3199.72075 samples/min Submissions: 20 -46.4 %
Blender 4.2.0 / OPTIX / Windows 5673.136912 samples/min Submissions: 51 3056.935657 samples/min Submissions: 273 -46.1 %
Blender 4.1.0 / OPTIX / Linux 6034.022292 samples/min Submissions: 7 3341.665328 samples/min Submissions: 9 -44.6 %
More tests: 3
Test and settingsNVIDIA GeForce RTX 3090 Ti NVIDIA GeForce RTX 4060Result difference¹
Blender 4.1.0 / OPTIX / Windows 5769.869986 samples/min Submissions: 32 3193.462191 samples/min Submissions: 147 -44.7 %
Blender 4.0.0 / OPTIX / Linux 6168.026652 samples/min Submissions: 16 3344.519949 samples/min Submissions: 11 -45.8 %
Blender 4.0.0 / OPTIX / Windows 5124.064923 samples/min Submissions: 111 3188.281304 samples/min Submissions: 229 -37.8 %

¹ Difference of the second result relative to the first in that row. No percentage is calculated for different upscaling algorithms. This compares published results, not a universal performance index.

Individual model tests

These results have no shared test of both models with the same version and settings. They are shown separately without a percentage difference.

NVIDIA GeForce RTX 3090 Ti

NVIDIA GeForce RTX 4060

More results: 107

Latest comparisons