Is This Thing On?

Before running a model, confirm the hardware is alive and the software can see it. One command, four chips, zero guessing.

Reading Your Hardware with tt-smi

tt-smi is the Tenstorrent System Management Interface. Your window into the chips. Run it in snapshot mode to get JSON instead of the interactive TUI:

tt-smi -s

A healthy QB2 returns four entries — one per Blackhole chip:

{
  "device_info": [
    {
      "board_type": "BLACKHOLE",
      "board_id": "AA-BHXY-0001",
      "pcie_speed": "GEN4",
      "pcie_width": "x16",
      "temperature": { "asic": 44.1, "inlet": 31.0 },
      "voltage": { "core": 0.85 },
      "power": { "total": 42.0 }
    }
  ]
}

Four entries in device_info means four chips, all alive. Check it directly:

tt-smi -s | python3 -m json.tool | grep board_type

You should see "BLACKHOLE" printed four times.

🌡️ Idle temperatures of 35–55°C are normal. Under full inference load, Blackhole chips run 70–85°C. The QB2 cooling system is sized for this. Hot chips doing real work is a good sign.
tt-smi -s showing four Blackhole chips on a QB2
tt-smi -s on a live QB2 — four Blackhole chips, JSON snapshot mode

Reading the Output

A healthy QB2 shows four entries in device_info. Look at each one for:

Count the entries:

tt-smi -s | python3 -c "import sys,json; d=json.load(sys.stdin); print(len(d['device_info']), 'devices')"

If you see 4 devices, move on. The QB2 is ready.

Chips enumerating means the hardware is alive — but the fastest proof it actually runs a model is the preloaded Qwen3-32B: launch tt-studio, pick it from the Deploy dropdown, and chat. No download. Full walkthrough in Your First Model.

If You See Fewer Than Four

A missing device usually means one of three things:

PCIe link not established:

dmesg | grep -i tenstorrent | tail -20

Look for errors about PCIe enumeration or firmware loading failure. A loose card is possible — the QB2 ships with cards seated, but transit happens.

Firmware mismatch:

tt-smi -s | python3 -m json.tool | grep -i fw_version

If firmware versions differ across devices, or show 0.0.0, you may need to reflash. See the tt-flash documentation for instructions.

Driver not loaded:

lsmod | grep tenstorrent

If nothing prints, the kernel driver isn’t loaded. This shouldn’t happen on a stock QB2, but if it does:

sudo modprobe tenstorrent
🔬 What tt-smi actually reads: The monitoring daemon talks to the chips via the kernel driver over PCIe. Temperatures come from on-chip thermal sensors. Power readings come from board-level current monitors. The data path: chip hwmon → kernel driver → tt-smi → your terminal. If a chip is missing from output, the driver never established a PCIe link to it.

Watching in Real Time

For a live view of all four chips while running inference:

tt-smi

This opens the interactive TUI — press q to quit. You’ll see per-chip utilization, temperature, and memory usage update live. Useful when a model is running and you want to see all four chips light up.

For something richer than the built-in TUI, tt-toplike renders the same telemetry as live ASCII art — every chip’s power, temperature, and DRAM state, animated:

tt-toplike host + chip view — live ASCII telemetry for the QB2 host and its four Blackhole chips
tt-toplike — the host and all four Blackhole chips, live telemetry as ASCII art
⬡ Tensix Grid — Blackhole (P100/P150/P300c / QB2)

This is what active inference looks like inside one chip. Four of these run in parallel on a QB2.

tt-smi -s on a live QB2 — four Blackhole chips, JSON snapshot output
tt-smi -s on a live QB2 — four Blackhole chips, JSON snapshot mode

Next: Installing the Stack →