# TorqHUB — stop paying for idle metal

> TorqHUB streams workloads onto the machines that can actually take them.

_The running section header_

_TorqHUB_

## Stop paying for idle metal

Your GPUs are reserved around the clock and work a sliver of that time. TorqHUB streams the load onto the machines that can actually take it.

[See it work](#emulator)

[Get access](#contact)

### Your capacity is mostly air

Reserved 24/7. Working, say, 18% of the time. Billed for 100% of it.

> **Note** — Illustrative — 10 racks reserved, 18% utilised.

### Occupied is not Used

A job holds the card for eight hours and computes for forty minutes. The card is busy. Nothing is happening.

_The occupancy slider_

### What it costs you

Move the sliders. This is the money that turns into heat and nothing else.

_The idle-cost calculator_

### Every job finds a GPU that fits

Different jobs, different shapes, different machines. Flip the switch and watch the gaps disappear.

_The live TorqHUB scheduler_

### The same air, at every scale

Small shop or full datacenter, a typical fleet runs near 18% utilised — reserved 24/7, working a sliver. Here's the monthly burn without TorqHUB, and what pooling reclaims with it.

#### Small business

A few cards, one team's apps.

3 GPUs

$3,290/mo

wasted without TorqHUB

$2,680/mo

saved with TorqHUB

At 3 GPUs, pooling reclaims about 2 idle machines.

#### Mid business

A room of GPUs, a dozen products.

8 GPUs

$9,280/mo

wasted without TorqHUB

$8,490/mo

saved with TorqHUB

At 8 GPUs, pooling reclaims about 6 idle machines.

#### Big business

A full rack at datacenter scale.

30 GPUs

$32,920/mo

wasted without TorqHUB

$30,780/mo

saved with TorqHUB

At 30 GPUs, pooling reclaims about 23 idle machines.

> **Note** — Illustrative — built from the same consolidation model as the live scheduler above, not a quote. Utilisation and per-GPU rates are tunable in config.

### One SDK token. Infinite scale.

You write the logic. We route the compute.

#### Install

One package, one token. No cluster to provision, no broker to configure.

#### Submit

Send a job with its type and payload. TorqHUB routes it to the GPU that fits.

#### Scale

Batch to hundreds, poll or await results. The router fills the gaps for you.

```ts
import { TorqClient } from '@torq/sdk'

const torq = new TorqClient({
  token: process.env.TORQ_TOKEN,
})

// submit a job — the router picks the GPU that fits
const job = await torq.jobs.submit('llm-70b', {
  model: 'meta-llama/Llama-3-70B',
  prompt: 'Summarize this transcript…',
})

// wait for the result (or poll, or batch to hundreds)
const result = await torq.jobs.wait(job.id)
```

### A mesh that's already running

Capacity where the work is. The router sees every node and every gap.

_The live mesh animation_

#### A single GPU, fully used

Even one card — local, on-prem, fully private. TorqHUB schedules the queue and loads/unloads models automatically, so a single GPU is reused evenly instead of idling between tasks.

#### Private corporate mesh

Pool the GPUs you already own into a closed, private mesh. TorqHUB redistributes compute across the fleet inside your walls — your jobs, your machines, nothing leaves the network.

#### Public crowd mesh

Or tap a crowdsourced pool: rent capacity on demand, or put your idle cards on the mesh and earn. The router streams every job to wherever the right GPU is free.

### Want the arithmetic behind these numbers?

The machine-readable version of this page carries every figure and where it comes from.

[Ask us](#m-contact)

_The contact form_

_Bands revealed on arrival_

_Declared motion_