Dead Quiet

Introducing the TT-QuietBox, our liquid-cooled desktop workstation for developers looking to run, test, and develop AI models.
Dead Quiet

Latest Thinking

Attention in SRAM on Tenstorrent Grayskull
Attention in SRAM on Tenstorrent Grayskull
When implementations of the Transformer's self-attention layer utilize SRAM instead of DRAM, they can achieve significant speedups.
Read more
Tenstorrent is Continuing its Contributions to the RISC-V Open Source Ecosystem
Tenstorrent is Continuing its Contributions to the RISC-V Open Source Ecosystem
Today we are pleased to announce the release of our RISC-V Architectural Compatibility Suite, now available in our GitHub repository.
Read more
The Ojo-Yoshida Report |  With Nvidia, It's Always Take It or Leave It
The Ojo-Yoshida Report | With Nvidia, It's Always Take It or Leave It
With its automotive SoC, Nvidia promises carmakers a licensable ASIL-D certified software stack. But OEMs face the dilemma of either getting locked into Nvidia or designing alternative stacks of their own with no adequate support from Nvidia.
Read more

Meet Galaxy.

Powered by 32 Wormhole™ processors, the rack-mounted Galaxy Wormhole Server delivers dense, high-performance AI compute.
Discover Galaxy
Meet Galaxy.

Now Open Source: TT‑Metalium™

TT-Metalium™ is great for customers who want to customize their models, write new ones, or even run non-machine learning code. No black boxes, encrypted APIs, or hidden functions.
Now Open Source: TT‑Metalium™

Have questions? We’re here to help.

Click one of the links below to get help with Tenstorrent products or services.
Support