Made for screws · Built for studs
Engineered in a garage,
by people who should
know better.
The world's most
over‑confident impact driver.
From £249Fictional. Not for sale.
ReserveReads the material, predicts the torque, and stops the instant the screw is home. TORQ makes the simplest drive feel considered.
TORQ‑1 Model Skip the film ↓A scroll film: one TORQ impact driver turns a full circle under a spotlight, a technical drawing plots it, then the camera moves in close on the grip.
TORQ isn't just an impact driver. It's the result of unprecedented AI* breakthroughs.
Intermission. TORQ‑1 is re‑reading the screw.
Skip to the specs ↓Reads the material. Predicts the torque. Stops the instant the screw is home.
TORQ‑1 is our open‑weight* model: 70 billion parameters, trained on 4.2 billion real‑world drives across 19 materials and one extremely stubborn flat‑pack wardrobe.
*Weights available on request. The asterisk is also AI‑generated. None of this is real. TORQ‑1 is not a model and TORQ is not a drill you can buy.
TORQ Pro, as tested. Each number says how we got it.
Claimed. Our own rig measured 1,560 in‑lbs, or 65%. Rigs are like that.
No load, full battery, quiet room.
Chuck empty, as is tradition.
Kitchen scale, the Pro’s 4.0Ah battery fitted.
Fits all three models. And nothing else.
In simulation.
Counted once. Then we stopped.
*In simulation. In your hands, results may include screws.
Tell TORQ‑1 what you're driving into. It will answer with a confidence it has not earned.
Every TORQ is carbon‑accounted, ethically argued with, and assembled by people who were told it was important.
RTX 4090 onboard
A flagship GPU, dedicated exclusively to rendering the LED work‑light at a buttery 240fps. Worth it.
Edge inference. TORQ‑1 runs entirely on the bit. No cloud, no Wi‑Fi. Your screws stay private. They've been through enough.
Always listening. A dedicated mic listens for the exact sound a screw makes a quarter‑second before it strips, then doesn't.
Drop‑tested. Survived a genuine three‑rung fall. Once. The driver was fine. The intern is recovering well.
Legacy support. Phillips, flathead, Torx, Pozidriv, hex, square, and that one cursed triangular one from the appliance.
Finishes. Available in eleven curated shades of off‑white, including 'Off‑White', 'White, Off', and 'Linen, Allegedly'.
Invented quotes. No real people, no ratings.
"Finally, an impact driver that respects me. It corrected my pilot hole and didn't make it weird."
"Assembled an entire flat‑pack wardrobe and cried zero (0) times. A personal record."
"Astonishingly fast. Keeps gently correcting my technique, which I did not ask for."
"It drove the screw before I'd finished deciding I wanted to. Mildly unsettling."
"Too intelligent. My deck now judges my life choices every time I walk across it."
"As a beaver, I have high standards for fastening. TORQ meets them. Could be quieter."
Peak torque, claimed in‑lbs
| Feature | TORQFor people who drive screws.£249 | Most opinionsTORQ ProFor people who drive a lot of screws.£449 | TORQ Pro MaxFor people the screws fear.POA or a sensible car |
|---|---|---|---|
| Power | |||
| Peak torque 1 | 1,800 in‑lbs 203 N·m | 2,400 in‑lbs 271 N·m | 3,600 in‑lbs 407 N·m |
| Impacts per minute 2 | 3,600 | 4,200 | 4,400 |
| No‑load speed 2 | 2,900 rpm | 3,400 rpm | 3,600 rpm |
| Brain | |||
| Model | TORQ‑1, quantized 4‑bit | TORQ‑1, full precision | TORQ‑1 Ultra, predictive everything |
| Behaviour | Stops before cam‑out, usually | Whispers encouragement | Ships with its own opinions |
| Battery and kit | |||
| In the box | 1 × 2.0Ah battery, charger | 2 × 4.0Ah batteries, charger, case | Self-charging (it won't say how) |
| Weight with battery 3 | 1.3 kg | 1.5 kg | 2.1 kg |
| Reserve TORQ | Reserve TORQ Pro | Enquire about TORQ Pro Max | |
Example data for a parody. Prices include VAT. None are for sale: TORQ is not real.
Pick a model. Nothing is saved, nothing is charged and nobody will email you.
We present TORQ‑1, a 70B‑parameter autoregressive model for next‑rotation prediction in fastener‑dense environments. By framing impact driving as a sequence‑modelling problem (each impact a token, each screw a sentence), TORQ‑1 achieves state‑of‑the‑art seating accuracy (99.94%, on the 12 screws we liked best) and a stripping rate indistinguishable from zero. We further show that scaling laws hold for torque, and that the model exhibits emergent reluctance to over‑tighten. We release the weights, the bits, and our regrets.
Peer‑reviewed by three carpenters and one structural engineer who asked to remain anonymous.