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.
Your capacity is mostly air
Reserved 24/7. Working, say, 18% of the time. Billed for 100% of it.
Occupied is not Used
A job holds the card for eight hours and computes for forty minutes. The card is busy. Nothing is happening.
Occupancy
How much of each reserved GPU is actually doing work. Drag to feel the gap.
Duty cycle slider. Current value 18 percent of reserved capacity. Range 5 to 60 percent. Use the left and right arrow keys to adjust by one percent.
What it costs you
Move the sliders. This is the money that turns into heat and nothing else.
The cost of waiting
Reserved GPUs burn money every hour they sit idle. Change the fleet — then drag the occupancy slider to watch the gap close.
Projected idle spend: $9,578 per month, $114,931 per year, at 18 percent duty cycle. less than one engineer / yr. Illustrative figures.
Every job finds a GPU that fits
Different jobs, different shapes, different machines. Flip the switch and watch the gaps disappear.
OFF — pinned to home GPUs
- DONE
- 64
- UTIL
- 29%
- QUEUE
- 36
- GPUS
- 3
ON — TorqHUB brokered + elastic
- DONE
- 129
- UTIL
- 16%
- QUEUE
- 5
- GPUS
- 3
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.
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.
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.
One GPU, used fully
A single card — local, on your desk, fully private. TorqHUB schedules the queue and loads/unloads models automatically, so even one GPU stays busy instead of idling between tasks.
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 usSTOP RENTING AIR
Tell us what you need. We'll come back with access, capacity or a deck.