A pool for the AI compute revolution.
modelOS turns every GPU forward pass into verifiable proof of work. Mine MDL with NoisyGEMM — every matrix multiplication counts.
The NetworkLive state of the pool
Active Miners
0
in PPLNS window
Blocks Found
—
all-time
Total Paid MDL
0 MDL
distributed to miners
Block height: —Pool fee: 2%PPLNS window: — shares
On-ChainPool wallet activity
Blocks Found
—
Total MDL Rewarded
0 MDL
PRL Rewards
—
Enable AuxPoW for PRL
Current Block
—
No blocks found yet.
Begin Mining
One command. Then your GPUs are mining MDL.
Download the miner, paste your address, and run. Rewards distributed automatically after maturity. Add a Pearl address to also earn PRL via AuxPoW.
Configuration
Generate your launch command
Required — block rewards paid here
Add your Pearl address to earn PRL via AuxPoW — pool handles the rest
pool.modeloslab.xyz:5566 (PPLNS) · pool.modeloslab.xyz:5567 (SOLO) · 2% fee
Inference FeesTwo income streams per GPU.
Block Rewards
Win the PoW race
Every NoisyGEMM forward pass generates verifiable proof of work. When your hash meets the target, you earn the MDL block reward.
Rewards are split proportionally via PPLNS and distributed after 100-block maturity on both chains.
Rewards are split proportionally via PPLNS and distributed after 100-block maturity on both chains.
Inference Fees
Win the inference race
Run vllm-miner and compete for paid AI inference jobs. When an
inference_tx confirms on-chain, all vllm-miners race to execute the prompt and submit a cryptographic proof. First confirmed proof earns the locked fee — no pool cut.| 7B model | 0.005 MDL base |
| 14B model | 0.02 MDL base |
| 32B model | 0.05 MDL base |
| 70B model | 0.10 MDL base |
Lookup
Check your earnings.
Enter your MDL wallet address to see your hashrate, workers, and payment history in real time.