What to Know About Your Workstation

Your workstation is a Tenstorrent Quietbox 2: four AI accelerators inside, an operating system you may not have used before, and the software stack already configured and waiting. The machine is ready to go — what’s left is knowing what you’ve got.

This guide doesn’t assume you know Linux, or Python, or what a PCIe slot is. It assumes you’re curious, and that curiosity is enough.

What’s Inside

The Tenstorrent Quietbox 2 (QB2) is a workstation with two Blackhole p300c cards — four Blackhole chips in total — on PCIe. Each p300c is a dual-chip card, and each chip is independent — four separate devices from the software’s point of view, connected to a standard CPU running Ubuntu 24.04 LTS.

What Detail
AI chips 2× Blackhole p300c cards (4 Blackhole chips)
Tensix cores per chip 120 (12×10 compute grid)
Connection PCIe Gen4 (4 independent devices)
OS Ubuntu 24.04 LTS
Pre-installed Drivers, tt-smi/tt-flash, the TT-Metalium and tt-inference-server containers, tt-studio
Source tree Not included — and neither is ~/tt-metal. TT-Metalium runs as a container (tt-metalium)

The chips don’t share memory. When you open device 0, you’re talking to one Blackhole chip. To use all four together, you use ttnn.CreateDevices({0, 1, 2, 3}) — not four separate open_device() calls.

⬡ Each Blackhole chip is a 17×12 Network on Chip (NoC) grid — 204 positions in total. Of those, 140 are Tensix compute tiles (120 are enabled on QB2's chips; the rest are harvested); the remainder are DRAM controllers, Ethernet cores for chip-to-chip links, the PCIe interface, and the routing fabric between them. The grid is how work moves — not through a shared bus, but through a programmable mesh of message-passing nodes.
Four Blackhole chips connected via PCIe to the CPU, with software stack and Python environments
🔌 Before anything else: power switch on the back panel to the ON position, then press the front power button. The fans spin up. That's the QB2 waking up. That sound is correct and expected.

What Ships Pre-Installed

Tenstorrent ships the QB2 ready to serve models. You don’t install drivers. You don’t compile anything. The full stack is already there:

What’s intentionally absent: ~/tt-metal — not just the source code, the whole directory. TT-Metalium reaches you as a container image instead, and tt-metalium is how you get inside it. You can build models, run inference, and work with the full API stack without ever having a checkout. Building from source is a later chapter — a much later chapter.

⚠️ Pre-installed is not the same as current. That list is the stack as it stood when your box was built — driver, firmware, tooling and container images all included. Upgrading is not most people's first instinct, and being behind almost never announces itself: it shows up as a tutorial that fails or hardware that looks broken. Once you've confirmed the chips respond (Chapter 3), take the upgrade step in Chapter 4 before you go looking for a bug.

Physical Tour

The QB2 looks like a standard tower workstation. On the inside:

The chips run warm under load. Fans will get louder when you run inference. This is correct. The cooling is designed for sustained operation at full chip temperature.

⬡ Tensix Grid — Blackhole (P100/P150/P300c / QB2)

One Blackhole chip. You have four, on two p300c cards.

Next: First Boot →