Network stats · SeedInfer

Network at a glance

99% revenue shareServing Gemma 4 26B · $0.03 / $0.20 per 1M

Run a node on your NVIDIA GPU

One command installs the agent, joins the network and starts serving. Providers keep 99% of what their GPU earns.

ECONOMICS · UNIT COST

Why 32GB VRAM is the threshold

Long-context inference is memory-bound: the economics are set by weights + KV-cache size, not FLOPs. Gemma 4 26B A4B NVFP4 with a 256K context needs a 32GB+ card to run without offload. 24GB cards are not supported yet.

Memory

256K context · NVFP4 weights

NVFP4 weights + FP8 KV cache + runtime overhead · 32GB min for headroom at 0.90 GPU memory utilization.

NVFP4FP8 KV32GB min

Compute

Marlin · FlashInfer · FP8

Blackwell-optimized kernels · chunked prefill · prefix caching · host 1:1 routing · no offload.

marlinflashinferfp8host 1:1

Power & retainer

Electricity = dominant cost

At scale, power dominates unit cost. Builder price covers electricity + profit split, and every node earns a standby retainer of $0.40/day per node with ≥50% uptime that day.

Provider 99%Protocol 1%

Revenue split

Builder pays$0.03 in / $0.20 out · 1M

↓

Provider99%

of token revenue · plus standby retainer $0.40/day per node with ≥50% uptime that day

↓

Protocol fee1%

Payouts: USDC on Base, monthly, minimum $1.00. Fiat payouts are not available.

Provider Revenue & Net-Profit Calculator

Real-World Hardware Economics

Line-by-line estimate for hosting models on an NVIDIA RTX 5090 32GB reference node. Providers receive 99% of token revenue (1% protocol fee) plus a standby retainer of $0.40/day per node with ≥50% uptime that day. Throughput and power figures are adjustable assumptions, not guarantees.

99% revenue share

Estimates, not guarantees

Earnings depend on real network demand. The network is at an early stage, so actual traffic per node may be far below the baseline assumption (200M input / 20M output tokens per day at 30% load). Payouts: USDC on Base, monthly, minimum $1.00.

Select Hosted Model StrategySelect model architecture to calculate yield

Active Rig Profile & Rates

NVFP4 · 256K ctx

GPU Hardware

NVIDIA RTX 5090 32GB

21,760 CUDA cores · 1,792 GB/s · 575 W TDP

Selected Model Rates

$0.03 in / $0.20 out

Per 1,000,000 processed tokens

Average GPU Card Utilization30% Average Load

5% (Low)30% (baseline assumption)100% (Full Capacity)

Daily Input Tokens200M / day

Rate: $0.03 / 1M input tokens

Daily Output Tokens20M / day

Rate: $0.20 / 1M output tokens

Electricity Tariff & Power Consumption$0.25 / kWh

$0.05 (Solar/US Low)$0.25 (EU Avg)$0.50 (High Tariff)

Avg Power Draw: 220 W average (TDP 575 W)

Monthly Energy: 158.4 kWh

Monthly Profit Summary

$269/mo net

Estimated net / month (Gemma 4 26B)

$269/ mo

After electricity, on 1× RTX 5090 32GB

Monthly Statement (30 Days)Gemma 4 26B

Token revenue (gross)$300.00

200M in × $0.03 + 20M out × $0.20 per day × 30

Your share (99%)+$297.00

1% protocol fee: -$3.00

Standby Retainer+$12.00

$0.40/day per node with ≥50% uptime that day (assumes every day qualifies)

Electricity Cost-$39.60

220 W avg (~158 kWh) @ $0.25/kWh

Net Monthly Profit$269.40

Formula: net = token revenue × 0.99 + $0.40 × 30 days − kWh × tariff. Payouts: USDC on Base, monthly, minimum $1.00.

Become a provider

NVIDIA GPU with ≥32GB VRAM · Ubuntu 24.04 LTS · vLLM + Docker · 24GB cards not supported yet

Platform Comparison: Vast.ai vs SeedInfer Freedom

Why P2P Inference Beats Traditional Rental Platforms

Full GPU Ownership & Flexibility

Traditional platforms like Vast.ai lock down your host system, demand 24/7 continuous availability, and grant tenant root/kernel access. SeedInfer runs as an isolated user-space container—giving you complete freedom to pause or use your GPU anytime without penalty.

Feature / Parameter	Vast.ai (Traditional Rental)	SeedInfer P2P Network
How you earn	Hourly rental while a tenant occupies the machine	99% of token revenue + $0.40/day per node with ≥50% uptime that day
GPU Owner Freedom & Flexibility	0% Freedom (Requires 24/7 non-stop availability or rating drops)	100% Freedom (Pause, game, render, or work anytime)
Host System & Privacy Security	Kernel / Root Access (Strangers get SSH access to host system)	Zero Kernel Access (Isolated Docker + Tailscale user-space)
Network Bandwidth Requirements	Min 1 Gbps Symmetric Fiber mandatory	Standard Consumer Broadband (Smart Prefix Caching)
Power Consumption & Heat Strain	Continuous full load while rented (up to 575 W TDP)	~220 W average at 30% load (~$40/mo @ $0.25/kWh)

CONCIERGE · WHITE-GLOVE

VIP Managed Node — we configure it for you

Remote Headscale join (tag:provider)
Attestation & verification
Gemma 4 26B A4B NVFP4 download & setup
Throughput benchmark on your GPU
Payouts in USDC on Base (monthly)
SLA & monitoring

≥32GB VRAM only · 24GB cards not supported yet

Managed onboarding is handled by the SeedInfer team. Open an issue on GitHub with your GPU model, VRAM and region and we will get back to you.

Request a managed node

Quick install

curl -fsSL https://seedinfer.com/install.sh | SEEDINFER_NODE_TOKEN=sipn_… bash

Create a node token in the Provider portal (sign-in required)

Roadmap · 4 phases

Roadmap · from electricity cost to parity

Phase 0 · Now (Q3 2026)

active

Gemma 4 26B A4B NVFP4 live

$0.03 / $0.20 per 1M · 256K context · 99% revenue share · standby $0.40/day per node with ≥50% uptime that day

Phase 1 · Q4 2026

coming soon

Nemotron 3.5 Lightning + Qwen 3.6 35B

1M-context Nemotron ($0.02 / $0.05) and Qwen ($0.06 / $0.50) · target 100 nodes · 99% share

Phase 2 · H1 2027

planned

Open provider marketplace

Target 300–1,000 nodes · more GPU classes · 99% share

Phase 3 · 2027+

vision

Electricity-price parity

Target: token prices approaching the electricity cost of inference · 99% share