Nexus Client

Lend your GPU. Earn GNN.

Run an eligible open model on hardware you already own, serve inference jobs for the Nexus network, and get paid in GNN for the compute you contribute.

Download client How it works Read the docs

How it works

  1. 1

    Install & pull a model

    Download the Nexus client and pull an eligible model with Ollama. The client detects your GPU and the model tiers it can serve.

  2. 2

    Init & stake

    Run nexus-client init to generate a node key and a fresh Solana wallet (or import your own), then nexus-client stake --amount 1 to send GNN on-chain to the network treasury so the gateway trusts your node. Staking is self-serve on mainnet — a 1 GNN minimum gets your node trusted by the gateway.

  3. 3

    Start earning

    Start the client and it joins the per-model queue. Completed jobs build reputation and pay out GNN every epoch.

Eligible models

These are the model classes accepted at launch. VRAM figures are honest minimums for usable throughput — more headroom means more concurrent jobs and higher tiers.

Model Tiers Min VRAM Quant notes
Hermes 3 8B ~10 GB (Q8) / ~6 GB (Q4) Q8 for best quality on a single consumer card; Q4 fits 8 GB GPUs with a small quality trade-off.
Kimi K2 Large MoE 2×80 GB-class, or hosted Sparse mixture-of-experts — not a single-consumer-GPU model. Realistically needs datacenter-class GPUs (e.g. dual 80 GB) or a hosted backend.
Qwen 2.5 — 7B / 14B / 32B ~8 GB (7B) / ~16 GB (14B) / ~24 GB (32B) VRAM scales with tier; figures assume Q4–Q5. 7B runs on most modern gaming GPUs; 32B wants a 24 GB+ card.

Download

Grab the client for your platform. Releases are published on GitHub.

macOS Apple Silicon (Intel) Linux x86_64, CUDA / ROCm Windows x86_64, CUDA

All releases & changelog →  ·  View source on GitHub →  ·  Checksums

Quickstart

Four commands from zero to earning. Replace the model with whichever eligible class your GPU can serve. 

# 1. Pull an eligible model
ollama pull llama3.2

# 2. Initialize your node + import a GNN-funded wallet
#    --model MUST match the Ollama model name exactly
nexus-client init --model llama3.2 --wallet import ./wallet.json

# 3. Stake GNN on-chain to the network treasury (mainnet, 1 GNN min)
nexus-client stake --amount 1

# 4. Start serving jobs and earning
nexus-client start

Full step-by-step docs →

Network stats

Live snapshot of the Nexus compute network.

— Nodes online
— Jobs served
— GNN paid