> For the complete documentation index, see [llms.txt](https://sn2-docs.inferencelabs.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sn2-docs.inferencelabs.com/miner-validator-resources.md).

# Miner/Validator Resources

Hardware requirements and setup for miners and validators

## Miners

Miners contribute to Subnet 2 by running inferences through zero-knowledge circuits. They receive requests from validators containing model IDs and input parameters, execute the model through a pre-generated circuit, and return outputs with cryptographic proofs.

Zero-knowledge proof generation is CPU-intensive, providing an opportunity for non-GPU miners to participate competitively.

### Hardware Requirements

#### Minimum

| Component      | Requirement   |
| -------------- | ------------- |
| CPU            | 8 core 3.2GHz |
| RAM            | 32GB          |
| Network Up     | 400Mbps       |
| Network Down   | 400Mbps       |
| Storage        | 1TB           |
| Storage Medium | NVMe SSD      |

#### Recommended

Exceeding these requirements in terms of storage, network, and CPU speed will result in higher rewards due to performance incentivization.

| Component      | Recommendation |
| -------------- | -------------- |
| CPU            | 8 core 3.6GHz+ |
| RAM            | 64GB+          |
| Network Up     | 1Gbps          |
| Network Down   | 1Gbps          |
| Storage        | 2TB            |
| Storage Medium | NVMe SSD       |

## Validators

Validators query miners, verify the proofs they return, and score them based on performance. Validators can accept external requests and route them through the network, or generate synthetic queries for benchmarking.

### Hardware Requirements

#### Minimum

| Component    | Requirement   |
| ------------ | ------------- |
| CPU          | 8 core 3.2GHz |
| RAM          | 16GB          |
| Network Up   | 400Mbps       |
| Network Down | 400Mbps       |
| Storage      | 1TB           |

#### Recommended

| Component      | Recommendation |
| -------------- | -------------- |
| CPU            | 8 core 3.4GHz  |
| RAM            | 32GB           |
| Network Up     | 1+Gbps         |
| Network Down   | 1+Gbps         |
| Storage        | 2+TB           |
| Storage Medium | SSD            |

## Setup

For installation and setup instructions, see the GitHub repository:

<https://github.com/inference-labs-inc/subnet-2>

### Quick Install

```console
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/inference-labs-inc/subnet-2/main/setup.sh)"
```

### Register on Subnet 2

```console
btcli subnet register --subtensor.network finney --netuid 2 --wallet.name {your_coldkey} --wallet.hotkey {your_hotkey}
```

## Scoring

Miners are scored based on:

| Metric          | Description                       |
| --------------- | --------------------------------- |
| Proof Validity  | Invalid proofs cause score decay  |
| Response Time   | Faster provers earn higher scores |
| Proof Size      | Smaller proofs are more efficient |
| Output Accuracy | Compared against baseline models  |

Valid proofs cause score recovery. The rate of recovery and maximum achievable score adjust based on a combined performance penalty weighting response time, proof size, and accuracy.