EXTERNAL TEST LAB

Test network changes
before they ship

A test environment for protocol upgrades, DevShards, inference flows, integrations and operational changes – before governance decisions or production rollout

Network dashboard ↗Inference dashboard ↗
OPERATE A HOST

How to Join node

git clone https://github.com/paranjko/external-test-lab.git
alias gdc="$PWD/external-test-lab/net-deployment-runbook/gdc.sh"
gdc host join --public-host <IP_or_DOMAIN> <ssh-alias>
Minimum Host requirements For more details, read Community DevNet runbook/JOIN: add a Host
ComponentMinimum
OSUbuntu 22.04, 24.04, or 26.04 (amd64)
GPUNVIDIA GPU with 16 GB VRAM
DriverNVIDIA R580 or newer
CUDAGPU works in a CUDA 12.8 Docker container
CPU8 threads or more (practical baseline)
Memory32 GB RAM or more (practical baseline)
Storage50 GiB free required, with 100–150 GB NVMe recommended
NetworkStable internet with a stable public IPv4 address or a DNS name that resolves to it
IngressTCP 80, 443, 5000, and the configured SSH port, plus UDP 443
UptimeAlways on with sleep and address changes disabled

Community DevNet currently runs Qwen/Qwen3-0.6B, its on-chain model profile declares v_ram: 16, check the live model registry, gdc does not accept a GPU from the VRAM number alone: qualification loads the model, checks /v1/models, completes an inference request, and records VRAM evidence, an 8 GB RTX 3070 may run this small model experimentally, but it is below the declared 16 GB and is not a guaranteed supported configuration

Chain ID–Shared ledger
Common model–Active group
Latest height–Advancing live
Largest voting share–Consensus distribution
LIVE DEVNET

Participant status

VALIDATOR MAP

Validator locations

Approximate public IP locations

LIVE GATEWAY LOAD

Inference traffic

Active requests–currently in flight
Input tokens–currently in flight
Successful requests–completed since gateway restart
Rate-limited requests–rejected since gateway restart
Network capacity–available model weight
Gateway trafficCHECKING
0 active now0 successful since restart0 rate-limited since restart