Contributor overview
Activity recorded under this public payout address. Contribution history remains visible when workers disconnect or leave.
Chain records are separate and may not exist until this address has indexed activity.
No contribution record for this address yet
This is a valid payout address. It does not need an on-chain transaction to appear here. Once a GPU client registers with this address, its availability and accepted work will be listed.
Connect a GPUConnected workers
Accepted participations
Historical response rate
Reported VRAM
SHARED MODEL · TESTNET
One Qwen3-32B model, across GPUs.
A connected GPU can still be downloading or loading. The complete model becomes available only when every required stage is ready.
0 / 2 required stages ready
0 active chats · 0 queued · — model slot capacity
Stage 1
Not readyLayers 0–47
0 ready · 1 assigned workers
Initial admission: 18.2 GiB free VRAM, followed by a real GPU probe.
Stage 2
Not readyLayers 48–63
0 ready · 3 assigned workers
Initial admission: 8.2 GiB free VRAM, followed by a real GPU probe.
Shared-model work is sponsored and currently earns no LIMO. Extra compatible workers can provide capacity or warm replicas. Waiting and unused replicas do not count as completed work.
Work and settlement
Accepted work and settled payments are separate events.
Cumulative settled earnings
Pending settlement
Escrow withdrawal balance
Paid participations
—Sponsored participations
—Failed participations
—Response history by model
Observed characters/s includes request preparation and network time. Historical rates remain visible while a worker is offline.
No observed response samples yet.
This measurement starts with newly accepted responses. Older work can have earnings and participation counts without an independently timed response sample.
Associated model profiles
No model information available.
Includes current registrations and models from retained work history. A listed profile does not mean that model is currently running; shared-model availability is shown separately above.
Resource reporting
- Freshly reported free VRAM
- —
- Accounting available since
- 2026-10-17 22:50:24 UTC
Memory values come from provider reports less than 45 seconds old. Missing or stale reports show —. Combined VRAM is not a promise that a larger model is ready.
Updated 2026-10-18 08:04:07 UTC · refreshes every 15 seconds
Contribute your GPUWork and earnings recorded since 2026-10-17 22:50:24 UTC. Earlier worker-only records are excluded when their payout cannot be verified.
What these numbers mean
Useful work, recorded
Work counts provider participations in coordinator-accepted requests. Multiple GPUs can participate in the same shared request. These counts are not proof of work or independent hardware verification.
Response rate, in context
Characters/s uses coordinator time from claim to accepted answer, including preparation and network time. A whole-group rate describes the shared answer, not one GPU. Rates are historical, model-specific and are never added together.
Earnings follow settlement
Earned totals include settled paid work. Sponsored requests and idle time earn no coins. Escrow withdrawal balances can also include chat refunds and are separate from earnings. Test LIMO has no monetary value.