Select processor 1
Select processor 2
NVIDIA GeForce GTX 1660 Ti
NVIDIA H100 SXM5

NVIDIA GeForce GTX 1660 Ti vs NVIDIA H100 SXM5. Specifications

User rating
star star star star star
Released
Q3/2019
NVIDIA GeForce GTX 1660 Ti
NVIDIA GeForce GTX 1660 Ti
Released
Q2/2022
User rating
star star star star star
NVIDIA H100 SXM5
NVIDIA H100 SXM5

What's the best choice NVIDIA GeForce GTX 1660 Ti or NVIDIA H100 SXM5? Which graphics card is faster?

Compare the available specifications of these models.

NVIDIA GeForce GTX 1660 Ti has a base frequency of 1.5 GHz. Memory size 6 GB. Memory type GDDR6. Released in Q3/2019.

NVIDIA H100 SXM5 has a base frequency of 1.065 GHz. Memory size 80 GB. Memory type HBM3. Released in Q2/2022.

Differences

  • Higher clock speed

    Around 41% better clock speed

    1.5 GHz left arrow 1.065 GHz

Positions in all rankings

Common positions NVIDIA GeForce GTX 1660 Ti GPU in popular benchmarks, for comparison with other models.

No data
Videokards Reasons to consider
NVIDIA H100 SXM5
Report a bug
  • More memory

    1233% more memory

    80 GB left arrow 6 GB

Positions in all rankings

Common positions NVIDIA H100 SXM5 GPU in popular benchmarks, for comparison with other models.

No data

Specifications

Technical data
NVIDIA GeForce GTX 1660 Ti NVIDIA GeForce GTX 1660 Ti
NVIDIA H100 SXM5 NVIDIA H100 SXM5
General info

Comparison of basic technical data of graphics cards NVIDIA GeForce GTX 1660 Ti and NVIDIA H100 SXM5, chip, information processing units.

  • Architecture
    Turing left arrow Hopper
  • CUDA Cores
    1536 left arrow -
  • Execution Units
    1536 left arrow 8448
  • GPU Chip
    TU116 left arrow GH100
  • L1 Cache
    64 KB left arrow 192 KB
  • L2 Cache
    1,536 MB left arrow 50 MB
  • Render Output Units
    48 left arrow 24
  • Texture Units
    96 left arrow 528
Memory settings

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

  • Memory Bandwidth
    288 GB/s left arrow 1,920 GB/s
  • Memory Bus
    192 bit left arrow 5120 bit
  • Memory Clock
    1500 MHz left arrow 1500 MHz
  • Memory Data Rate
    12 Gbps left arrow 3 Gbps
  • Memory Size
    6 GB left arrow 80 GB
  • Memory Type
    GDDR6 left arrow HBM3
Clock frequency

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

  • Base Clock
    1500 MHz left arrow 1065 MHz
  • Boost Clock
    1770 MHz left arrow 1780 MHz
Thermal Management

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

  • Graphics Card Power
    120 W left arrow -
  • Maximum GPU Temperature
    95 °C left arrow -
  • System Power Supply
    450 W (Minimum system power requirement) left arrow 1100 W (PSU recommendation)
  • TDP
    120 W left arrow 700 W
  • Board Number
    - left arrow PG520
Interfaces

Connectivity and connections.

  • DisplayPort Ports
    1 × DisplayPort 1.4a left arrow -
  • DVI Ports
    1 × DVI left arrow -
  • HDMI Ports
    1 × HDMI 2.1 left arrow -
  • Max. Displays
    3 left arrow 1
  • Other Display Outputs (unparsed)
    DP 1.4a; HDMI 2.0b; DL-DVI-D left arrow -
  • PCIe Interface
    PCIe 3.0 x16 left arrow PCIe 5.0 x16
  • Power Connectors
    8-pin left arrow 8-pin EPS
Technical data

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

  • CUDA
    7.5 left arrow 9.0
  • DirectX
    12.1 left arrow No
  • Max. resolution
    3840 × 2160 left arrow 3840x2160@60Hz
  • OpenCL
    3.0 left arrow 3.0
  • OpenGL
    4.6 left arrow No
  • Shader Model
    6.7 (6.4) left arrow No
  • Vulkan
    1.3 left arrow No
Dimensions

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

  • Height
    35 mm left arrow -
  • Length
    229 mm left arrow -
  • Slot Size
    Dual-slot left arrow -
  • Width
    111 mm left arrow -
More information

Comparison of interfaces and release dates for GPU NVIDIA H100 SXM5 and NVIDIA GeForce GTX 1660 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 -
  • Multi-monitor support
    Yes left arrow -
  • Official source
    https://www.nvidia.com/en-us/geforce/graphics-cards/compare/ left arrow -
  • Process Technology
    12 nm left arrow 4 nm
  • Release date
    Q1/2019 left arrow Q2/2022
  • Verification scope
    Explicit manufacturer fields refreshed; other original historical fields retained, not all reverified. Partial composite conflicts are preserved. left arrow -
  • Verified on
    2026-09-30 left arrow -
Theoretical Performance

  • FP16 (theoretical)
    10.87 TFLOPS (2:1) left arrow 120.3 TFLOPS
  • FP32 (theoretical)
    5.437 TFLOPS left arrow 30.07 TFLOPS
  • FP64 (theoretical)
    169.9 GFLOPS (1:32) left arrow 15.04 TFLOPS
  • Pixel Rate
    84.96 GPixel/s left arrow 42.72 GPixel/s
  • Texture Rate
    169.9 GTexel/s left arrow 939.8 GTexel/s

Benchmarks

Performance tests GPUs

No comparable benchmark results are available yet. Specifications alone do not determine which model is faster.

These are saved results from the earlier catalog. Measurement dates and test configurations were not recorded. Models with no comparable results are omitted.

Recent models: test results with identified primary sources — Game frame rates

Latest comparisons