🐝About Sogni Fast Worker

Sogni Fast Worker is a Docker-based service for contributing supported NVIDIA GPU capacity to the Sogni Supernet. It can run on a dedicated Windows or Linux machine, on an NVIDIA DGX Spark, on an otherwise-idle personal system, or on a GPU hosting platform that supports custom containers.

After installation, use dashboard.sogni.ai/fast-workers to check status, configure downtime alerts, inspect jobs and earnings, review health telemetry, and change settings supported by the worker. See Using the Workers Dashboard for a complete tour.

#Choose a worker type

There are two current Fast Worker types, plus one two-machine deployment:

Comfy Worker has three hardware builds: x86-64 for ordinary NVIDIA desktop and server hosts, Linux ARM64 for discrete Blackwell GPUs, and a separate Linux ARM64 build for NVIDIA DGX Spark. Each updates independently. The installer selects the matching image; mixed integrated/discrete hosts need an explicit supported GPU assignment. See the ARM64 RTX release notes or DGX Spark release notes for the requirements and supported scope.

The standalone Stable Diffusion Worker is retired as of October 27, 2026. Existing operators should migrate to Comfy Worker. The former Flux Worker is also retired; Comfy serves current Flux-family workflows.

Available models and their resource requirements change with the production catalog. Which jobs your hardware can take explains the GPU VRAM and host RAM each job type needs and how to set up a machine for the most jobs. Consult the live Comfy workflow catalog before sizing a machine. A generic GPU name or VRAM total does not guarantee eligibility for every workflow.

You can change worker type by running the current installer again. A worker advertises only the workloads compatible with its type, GPU, cached files, and operator settings.

#Requirements

Before installing, provide:

1. A Sogni account. Use one primary account and create a separate Fast Worker NFT token ID for each simultaneously running GPU worker.
2. A supported NVIDIA GPU, or an NVIDIA DGX Spark. Some current workloads begin at 16 GB of VRAM; others require 20 GB, 24 GB, 32 GB, or more. The worker filters the live catalog for the detected hardware, and a DGX Spark is limited further to the workflows qualified on that machine.
3. Docker Desktop using its Linux/WSL2 backend on Windows, or Docker Engine with NVIDIA Container Toolkit on Linux. A DGX Spark uses the Linux path on ARM64.
4. Enough host RAM and fast persistent storage for the chosen workflows. For MiniMax H3 and LTX video on a 24/32 GB GPU, the worker needs 47 GiB of usable RAM (a 50 GB Docker/WSL allocation to be safe); see hardware requirements. Comfy model storage can reach several hundred gigabytes and changes as workflows are added or retired. Reserve additional space for Docker images, temporary downloads, logs, and the operating system.
5. Stable Internet access, safe power delivery, and physical cooling sized for sustained GPU compute.
6. A Sogni API key and the unique Fast Worker NFT token ID. Create a worker key on the API Keys page: it signs in workers but cannot start paid work. Your account's Original key also works; a developer key does not. The interactive installer guides the initial authentication. A Fast Worker NFT is a paid mint: mint one for each GPU worker at nft.sogni.ai, where the current mint price is shown. It is paid in ETH on Base, plus network gas.

You can mint additional Worker NFTs directly to your existing Sogni account, with no per-account mint limit while supply is available. Fund that account's wallet with ETH on Base, then mint each NFT separately at the displayed price plus gas. No extra accounts or transfers are needed. See buying additional Worker NFTs for the steps.

#How earnings work

A connected worker advertises eligible workloads, receives jobs from the Supernet, and is credited for successfully completed work under the applicable payment path.

• Regular Spark- and SOGNI-paid jobs credit worker earnings as jobs complete.
• Unlimited subscription-covered jobs are an optional second path accounted through the monthly Worker Subscription Revenue Share Pool. Review participation and results in Subscription Earnings.

For a dated, hardware-by-hardware outlook, read What an Nvidia GPU earns on Sogni in Sept 2026. It combines pay-as-you-go work and the Unlimited subscription pool using eight complete days of activity across 133 ComfyUI workers. The September scenarios make uptime and pool-growth assumptions explicit; they are forecasts before operating costs, not settled payouts.

Demand, job mix, worker speed, availability, model eligibility, network policy, payment values, and operating costs all vary. Historical dashboard or leaderboard results are not a promise of future workload, revenue, profit, or cost recovery.

#Start here

#Terms and support

Operating a worker is governed by the Sogni Terms of Service and Privacy Policy. The Terms include the controlling provisions for Worker operation, operator responsibilities, eligibility, rewards, warranties, and liability; this setup guide does not replace them.

For help, email [email protected] or join the Sogni Discord.