Skip to main content

Requirements

The machine

MinimumRecommended
OS64-bit Linux (kernel 5.x+), or Windows 11 + WSL2Ubuntu 22.04 / 24.04 LTS
GPUNVIDIA, 6 GB VRAM16–24 GB+ VRAM
NVIDIA driver575+ (CUDA 12.9)Latest stable
CPU4 cores8+ cores
RAM8 GB32 GB+
Free disk50 GB SSD100 GB+ NVMe SSD
Network25 Mbps down, stable100 Mbps+ symmetric

Only two things are installed by you: Docker and the NVIDIA driver. Everything else ships in the image.

Which GPUs earn what

VRAM decides which models your card can hold, and that decides what it can be rented for. More VRAM is worth more than more speed.

TierVRAMExample cards
Entry6–8 GBRTX 2060, 3050 / 3060, 4060 / 4060 Ti, 5060 (incl. Laptop)
Standard10–12 GBRTX 3080, 2080 Ti, 4070 / 4070 Ti, 5070
High16 GBRTX 4070 Ti Super, 4080 / 4080 Super, 5070 Ti / 5080
Premium24–32 GBRTX 3090 / 3090 Ti, 4090 / 4090 D, 5090, RTX 4000–5000 Ada, A10
Pro / Datacenter48 GB+A40, RTX 6000 Ada, RTX PRO 5000/6000 Blackwell, A100, H100, H200

NVIDIA only. AMD and Intel cards are not supported, and neither is Apple silicon. The inference engine the agent runs is CUDA-only.

Laptop cards count. A laptop 3060 with 6 GB is a real Entry-tier host.

Network

  • Outbound to our backend, to Hugging Face for model weights, and to Cloudflare for the tunnel that carries inference traffic.
  • No inbound ports and no port forwarding. The tunnel is outbound, so the agent works behind NAT and consumer routers without any configuration.
  • Stability beats speed. The agent heartbeats continuously and is marked offline if it stops answering. A steady 25 Mbps line is a better host than a fast one that drops.
Changing networks needs a restart

Docker fixes a container's DNS when it is created. Moving the machine between networks silently breaks it until the container is restarted — the --dns flags in the install commands prevent this. See Troubleshooting.

Power and uptime

Your GPU only earns while it is online and idle enough to accept work. Two things quietly cost hosts money:

  • Sleep. A machine that suspends stops serving, and a job in flight fails.
  • Gaming or rendering on the same card. The agent measures free VRAM, so a busy card is offered smaller jobs or none at all.

A host does not need to be a dedicated machine, but the more predictable its free time, the more work it gets.

What the agent does to your machine

  • Runs one container, plus one more per job while a job is running.
  • Writes job workspaces to /var/lib/neurogrid/workloads.
  • Stores its encrypted token in a Docker volume, not in your home directory.
  • Needs the Docker socket, which is root-equivalent access to the host. The container is packaging, not a security boundary — run it on a machine you are comfortable giving that to.