NVIDIA H100 is a data-center GPU for large AI model training and inference.
The NVIDIA H100 is a data-center GPU built for large language model and AI training and inference workloads, using the Hopper architecture with a Transformer Engine.
NVIDIA states it speeds up large language model workloads and improves GPT-3-scale training throughput relative to the prior A100 generation.
Intel
Gaudi
intel.com
Advanced Micro Devices
Instinct
amd.com
MatX
MatX One
matx.com
NextSilicon
Maverick-2
nextsilicon.com
Alphabet
TPU
abc.xyz
Volantis
Volantis A-1
volantissemi.ai
| Attribute | Nvidia H100 | Gaudi | Instinct | MatX One | Maverick-2 | TPU | Volantis A-1 | |
|---|---|---|---|---|---|---|---|---|
| Provider | | | | | | | | |
| Founded | 1993 | 1968 | 1969 | 2022 | 2017 | 1998 | 2022 | |
| Sells To | Consumers, Enterprise | Enterprise | Consumers, Enterprise | Technology Companies | — | Consumers, Enterprise | — | |
| Pricing Model | Licensing, Product Sales, Subscription | Hardware Sales | Software, Transactional | Pre-Revenue | — | Advertising, Recurring, Transactional | — | |
| Ownership | Public | Public | Public | Private | Private | Public | Private |
Provider
Founded 1993
Sells To Consumers, Enterprise
Pricing Model Licensing, Product Sales, Subscription
Ownership Public
Provider
Founded 1968
Sells To Enterprise
Pricing Model Hardware Sales
Ownership Public
Provider
Founded 1969
Sells To Consumers, Enterprise
Pricing Model Software, Transactional
Ownership Public
Provider
Founded 2022
Sells To Technology Companies
Pricing Model Pre-Revenue
Ownership Private
Provider
Founded 2017
Sells To —
Pricing Model —
Ownership Private
The HP ZGX Nano AI Station is a compact desktop AI development system from HP.
The ASUS Ascent GX10 is a compact desktop AI supercomputer built on the NVIDIA GB10 superchip.
Dell Pro Max with GB10 is Dell's compact desktop AI development system built on the NVIDIA GB10 superchip.
HPE Cray XD670 is a 5U AI training server supporting eight NVIDIA H100 or H200 SXM5 GPUs.
Supermicro server systems powered by NVIDIA RTX PRO Blackwell Server Edition GPUs for enterprise AI, HPC, and visual computing.
Open-source USD price per GPU-hour across H100, H200, B200, and B300, refreshed every 15 minutes.
Verified-counterparty venue trading GPU hardware, reserved rental, and forward contracts.
GPU-as-a-Service platform providing on-demand NVIDIA GPU cloud solutions for AI, ML, and HPC workloads
Tenstorrent PCIe accelerator card family for AI training and inference workloads.
The HP ZGX Nano AI Station is a compact desktop AI development system from HP.
The ASUS Ascent GX10 is a compact desktop AI supercomputer built on the NVIDIA GB10 superchip.
Dell Pro Max with GB10 is Dell's compact desktop AI development system built on the NVIDIA GB10 superchip.
HPE Cray XD670 is a 5U AI training server supporting eight NVIDIA H100 or H200 SXM5 GPUs.
Supermicro server systems powered by NVIDIA RTX PRO Blackwell Server Edition GPUs for enterprise AI, HPC, and visual computing.
Open-source USD price per GPU-hour across H100, H200, B200, and B300, refreshed every 15 minutes.
Verified-counterparty venue trading GPU hardware, reserved rental, and forward contracts.
GPU-as-a-Service platform providing on-demand NVIDIA GPU cloud solutions for AI, ML, and HPC workloads
SambaNova DataScale is a data-center AI computing platform.
Tenstorrent PCIe accelerator card family for AI training and inference workloads.
