Pearl Mining¶
OpenJarvis can mine the Pearl Proof-of-Useful-Work chain through local LLM
inference. The primary v1 path supports NVIDIA H100/H200 hosts running vLLM
with Pearl's Docker miner. The consolidated Pearl integration also includes
experimental Apple Silicon and CPU providers through the same MiningProvider
registry.
Prerequisites¶
| Requirement | v1 expectation |
|---|---|
| GPU | NVIDIA H100 or H200, sm_90a class, at least 70 GB VRAM |
| OS | Linux with nvidia-container-toolkit configured |
| Docker | Docker 24+ with GPU runtime access |
| Disk | At least 200 GB free for the 70B model and build cache |
| Pearl node | Reachable pearld JSON-RPC endpoint, default http://localhost:44107 |
| Wallet | Pearl address beginning with prl1q or prl1p |
The default vLLM config uses gpu_memory_utilization = 0.96 and
max_model_len = 8192 for the Pearl 70B mining model on H100/H200 80 GB GPUs.
To generate a wallet address with Pearl's Oyster wallet, run Pearl's wallet
daemon and query it with prlctl --wallet --skipverify -s localhost:44207
getnewaddress. Do not reuse a wallet whose mnemonic has been pasted into logs,
chat, or issue trackers.
Quick Start¶
uv sync --extra mining-pearl-vllm
export PEARLD_RPC_PASSWORD=<your-pearld-password>
export HF_TOKEN=<your-huggingface-token>
uv run jarvis mine init
uv run jarvis mine start
uv run jarvis mine status
mine init writes a [mining] config section and resolves the Pearl Docker
image. If Pearl has not published a suitable image for the pinned ref,
OpenJarvis falls back to building from the pinned Pearl source checkout. First
builds can take 30-60 minutes.
On a shared NVIDIA host, restrict the miner to idle GPUs:
This writes [mining.extra].cuda_visible_devices, which mine start passes to
Docker instead of exposing every GPU on the machine.
Commands¶
jarvis mine modelslists Pearl model support status.jarvis mine inspect-modelchecks a Pearl model artifact before GPU launch.jarvis mine doctorprints hardware, Docker, Pearl node, wallet, provider, and session checks.jarvis mine initwrites the local mining config and resolves the image.jarvis mine startlaunches the Pearl miner container and writes the runtime sidecar.jarvis mine stopstops the provider and removes the sidecar.jarvis mine statusreads live gateway metrics.jarvis mine attachwrites a sidecar for a miner you launched manually.jarvis mine logsprints the Docker container log tail.jarvis mine validate-modelprobes the active vLLM miner and gateway before promoting a planned Pearl model to validated.
Model Support¶
Run:
OpenJarvis only enables models that have Pearl-compatible quantized artifacts
and real hardware validation. Raw Hugging Face models such as
Qwen/Qwen3.5-9B or google/gemma-4-E4B-it are not mineable by themselves;
they need corresponding Pearl-compatible variants.
The validated models are:
pearl-ai/Llama-3.3-70B-Instruct-pearl
ScalingIntelligence/Gemma-4-31B-it-pearl
ScalingIntelligence/Qwen3.5-9B-pearl
The Gemma 31B and Qwen 3.5 9B artifacts are experimental private staging
artifacts under the ScalingIntelligence Hugging Face org. You need Hugging
Face access to those repos before OpenJarvis can inspect or run them. They were
validated on H100 with jarvis mine validate-model, but the short validation
runs did not find a reward-bearing block or accepted share.
When validating a newly converted Pearl model on a mining host, run:
jarvis mine inspect-model \
--model ScalingIntelligence/Qwen3.5-9B-pearl
jarvis mine validate-model \
--model ScalingIntelligence/Qwen3.5-9B-pearl \
--prompt "Say hello in one sentence." \
--output qwen3.5-9b-pearl-validation.json
Attach the JSON artifact to the validation issue when promoting additional models.
v1 Scope¶
v1 is solo mining only. OpenJarvis does not take fees, custody funds, generate
wallet keys, run pools, or operate pearld. Users provide their own Pearl node
and payout address.
Unsupported in this PR:
- Pool mining and the future 20% OpenJarvis fee model
- AMD GPU mining and non-Pearl backends
- RTX 4090 or other non-Hopper NVIDIA GPUs
- Wallet generation or transaction signing inside OpenJarvis
Troubleshooting¶
Run:
Read the rows top-down. Fix the first failing dependency before retrying
mine start. A Mac or AMD machine should fail honestly at provider capability;
those paths are expected to land as separate providers.
Production Readiness¶
The NVIDIA path requires one real H100/H200 validation run before it should be
marketed as a proven earning path. The developer runbook is
../development/mining-nvidia-validation.md.