Tenstorrent Wormhole Instances are Now Available Via Koyeb Cloud

February 25, 2025 -- Tenstorrent is announcing the availability of Tenstorrent Wormhole™ Instances via the Koyeb Serverless Platform. You can now access the Wormhole™ multi-chip solution in minutes to bring up and test frontiers of model inference performance.

Tenstorrent is committed to getting developers access to their hardware and giving them the ability to work on their open-source software stack, which is why they’re excited to use Koyeb’s hardware-agnostic cloud infrastructure to enable on-demand access to the Tensix Processor and their open-source TT-Metalium SDK.

Two instance types will be available via the Koyeb Cloud:

• TT-n300s: With one n300s, this instance has 24GB of GDDR6, 192MB of SRAM, provides up to 466 FP8 TFLOPS, and comes with 64GB of RAM with 4 vCPU.
• TT-Loudbox: With 4x n300s meshed together, this instance has 96GB of GDDR6, 768MB of SRAM, provides up to 1864 FP8 TFLOPS, and comes with 256GB of RAM with 16 vCPU.

These instances come with all the native features of the Koyeb platform to reduce developers time to build AI models and run inference workloads in on-demand environments, with zero infrastructure management. Features of the platform include:

• Instant Development Environments with the ability to deploy containers running the Tenstorrent open-source SDKs in a minute
• Fast NVMe volumes to persist data in development environments
• Continuous deployment with automatic build of your Dockerfiles
• Scale-to-zero and autoscaling for production serverless inference endpoints
• Built-in Observability to analyze logs and metrics

“On demand access enables developers to experience Tensix processors in a minute - allowing them to develop, test and run their models faster," Jim Keller, CEO of Tenstorrent. "Cloud access is important to us because we want developers to be able to try our technology and see that we are serious about their experience and their feedback before committing to ownership. This is one of the ways we enable them to own their future."

All instances released today are equipped with Tenstorrent Wormhole n300s cards. Wormhole is Tenstorrent’s first generation Tensix Processor, built with Tensix Cores, each of which includes a compute unit, Network-on-Chip, local cache, and “baby RISC-V” cores, resulting in uniquely efficient data movement through the chip. Development on these cards is supported by Tenstorrent’s open source TT-NN and TT-Metalium SDKs.

“I had the privilege of get an early demo from the Koyeb and Tenstorrent teams, and it’s a game-changer,” said Erik Kaunismäki, a SW Engineer at Hugging Face. “Instantly accessing Tenstorrent hardware in seconds makes it effortless to build and hack on Wormhole multi-chip solution.”

The Wormhole ASIC is designed to scale, featuring a Network-on-Chip (NoC) that offers 3.2 Tbps of Ethernet connectivity to surrounding chips, and we're releasing an instance equipped with four meshed n300s leveraging this capability. If you're familiar with the Tenstorrent ecosystem, this is equivalent to a TT-LoudBox system in terms of accelerator computing.

These instances are available now in private preview – please navigate to Koyeb’s site to request access to on-demand Tenstorrent instances.