B200 vs H200 NVL

#ad 
Buy on Amazon
VS

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the rankingnot ratednot rated
Place by popularitynot in top-100not in top-100
ArchitectureHopper (2022−2024)Blackwell (2024−2025)
GPU code nameGH100GB100
Market segmentWorkstationWorkstation
Release date18 November 2024 (1 year ago)2024 (2 years ago)

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores1689618944 ×2
Core clock speed1365 MHz700 MHz
Boost clock speed1785 MHz1965 MHz
Number of transistors80,000 million104,000 million
Manufacturing process technology5 nm5 nm
Power consumption (TDP)600 Watt1000 Watt
Texture fill rate942.51,163.3 ×2
Floating-point processing power60.32 TFLOPS74.45 TFLOPS ×2
ROPs2424 ×2
TMUs528592 ×2
Tensor Cores528592 ×2
L1 Cache33 MB37 MB
L2 Cache50 MB50 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

InterfacePCIe 5.0 x16PCIe 5.0 x16
Length267 mmno data
Width2-slotSXM Module
Supplementary power connectors8-pin EPSno data

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory typeHBM3eHBM3e
Maximum RAM amount141 GB90 GB ×2
Memory bus width6144 Bit4096 Bit ×2
Memory clock speed1593 MHz2000 MHz
Memory bandwidth4.89 TB/s4.1 TB/s ×2
Resizable BAR++

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display ConnectorsNo outputsNo outputs

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectXN/AN/A
Shader ModelN/AN/A
OpenGLN/AN/A
OpenCL3.03.0
VulkanN/AN/A
CUDA9.010.0
DLSS++

Synthetic benchmarks

Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.



GeekBench 5 OpenCL

Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.

H200 NVL 335140
B200 346048
+3.3%

Pros & cons summary


Maximum RAM amount 141 GB 90 GB
Power consumption (TDP) 600 Watt 1000 Watt

H200 NVL has a 57% higher maximum VRAM amount, and 67% lower power consumption.

We couldn't decide between H200 NVL and B200. We've got no test results to judge.

Other comparisons

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


3.3 44 votes

Rate H200 NVL on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

No user ratings yet.

Rate B200 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about H200 NVL or B200, agree or disagree with our ratings, or report errors or inaccuracies on the site.