> ## Documentation Index
> Fetch the complete documentation index at: https://justme-8834e675-codex-docs-0-4-44.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# What is AINode?

> Turn any NVIDIA GPU into a complete local AI platform.

<img src="https://mintcdn.com/justme-8834e675-codex-docs-0-4-44/yQQjVu6VlAg0xzJZ/ainode-logo.png?fit=max&auto=format&n=yQQjVu6VlAg0xzJZ&q=85&s=8e92c2bca848cc2d2c5fbe72ee7c3a2b" alt="AINode" width="120" style={{ margin: "0 auto 2rem", display: "block" }} data-path="ainode-logo.png" />

AINode is a free, open-source platform that turns any NVIDIA GPU machine into a complete local AI stack — browser chat UI, OpenAI-compatible API, LoRA fine-tuning, and automatic multi-node clustering over NCCL.

**One command to install. No cloud. No monthly bill.**

```bash theme={null}
curl -fsSL https://ainode.dev/install | bash
```

***

## Key capabilities

<CardGroup cols={2}>
  <Card title="Chat UI" icon="message" href="/guides/chat">
    Browser-based streaming chat on port 3000. Works with any loaded model.
  </Card>

  <Card title="OpenAI-compatible API" icon="code" href="/api-reference/chat">
    Drop-in `/v1` endpoints on port 8000. Works with LangChain, Open WebUI, and any OpenAI client.
  </Card>

  <Card title="Model downloads" icon="download" href="/guides/models">
    50+ models from the built-in catalog. Paste any Hugging Face repo ID.
  </Card>

  <Card title="Fine-tuning" icon="brain" href="/guides/training">
    LoRA, QLoRA, and full fine-tune from the browser. No notebooks.
  </Card>

  <Card title="Quantization" icon="compress" href="/guides/quantize">
    Compress any model to AWQ or NVFP4 on your own GPU, then serve it or push it to Hugging Face.
  </Card>

  <Card title="Multi-node clustering" icon="server" href="/guides/distributed">
    Automatic peer discovery. One model sharded across all GPUs in the cluster.
  </Card>

  <Card title="Federated serving" icon="network-wired" href="/guides/federation">
    One endpoint, many models — the master routes each request to the node that holds the model.
  </Card>

  <Card title="Model stacking" icon="layer-group" href="/guides/federation">
    Run several models per node. They persist across restarts and replay on boot.
  </Card>

  <Card title="Prometheus metrics" icon="chart-line" href="/api-reference/metrics">
    `/metrics` endpoint for Grafana, Prometheus, VictoriaMetrics.
  </Card>
</CardGroup>

***

## Verified hardware

### GB10 Grace Blackwell systems (unified memory, cluster-native)

| Hardware                    | Manufacturer | GPU memory     | Price   | Status                            |
| --------------------------- | ------------ | -------------- | ------- | --------------------------------- |
| DGX Spark                   | NVIDIA       | 128 GB unified | \$3,999 | ✅ Verified — TP=4, 487 GB cluster |
| Ascent GX10                 | ASUS         | 128 GB unified | \$2,999 | ✅ Verified                        |
| Pro Max with GB10 (FCM1253) | Dell         | 128 GB unified | TBD     | ✅ Supported                       |
| ZGX Nano AI Station         | HP           | 128 GB unified | TBD     | ✅ Supported                       |

All GB10 systems share the same core: NVIDIA Blackwell GPU + Arm Grace CPU on NVLink-C2C, 1 petaFLOP FP4, dual-port ConnectX-7 fabric. Connect two units with the NVLink Bridge for TP=2 (244 GB VRAM, \~\$6–8K total).

### Data center / AI accelerators

| GPU              | VRAM            | Architecture | Tier                 |
| ---------------- | --------------- | ------------ | -------------------- |
| B200             | 192 GB HBM3e    | Blackwell    | Data center          |
| H200             | 141 GB HBM3e    | Hopper       | Data center          |
| H100 SXM5 / PCIe | 80 GB HBM3      | Hopper       | Data center          |
| A100 80 GB       | 80 GB HBM2e     | Ampere       | Data center          |
| A100 40 GB       | 40 GB HBM2e     | Ampere       | Data center          |
| L40S             | 48 GB GDDR6 ECC | Ada Lovelace | Inference / viz      |
| L40              | 48 GB GDDR6 ECC | Ada Lovelace | Inference / viz      |
| A40              | 48 GB GDDR6 ECC | Ampere       | Data center / viz    |
| L4               | 24 GB GDDR6 ECC | Ada Lovelace | Edge inference (72W) |
| A30              | 24 GB HBM2      | Ampere       | Data center          |
| A10              | 24 GB GDDR6 ECC | Ampere       | Inference            |
| A16              | 4× 16 GB GDDR6  | Ampere       | VDI                  |
| A2               | 16 GB GDDR6     | Ampere       | Edge                 |

### Professional workstation

| GPU                    | VRAM            | Architecture | Tier            |
| ---------------------- | --------------- | ------------ | --------------- |
| RTX PRO 6000 Blackwell | 96 GB GDDR7 ECC | Blackwell    | Pro workstation |
| RTX 6000 Ada           | 48 GB GDDR6 ECC | Ada Lovelace | Pro workstation |
| RTX 5000 Ada           | 32 GB GDDR6 ECC | Ada Lovelace | Pro workstation |
| RTX 4500 Ada           | 24 GB GDDR6 ECC | Ada Lovelace | Pro workstation |
| RTX 4000 Ada           | 20 GB GDDR6 ECC | Ada Lovelace | Pro workstation |
| RTX A6000              | 48 GB GDDR6 ECC | Ampere       | Pro workstation |
| RTX A5000              | 24 GB GDDR6 ECC | Ampere       | Pro workstation |
| RTX A4000              | 16 GB GDDR6 ECC | Ampere       | Pro workstation |
| RTX A2000 12 GB        | 12 GB GDDR6 ECC | Ampere       | Pro entry       |

### Consumer — GeForce RTX 50 series (Blackwell, 2025)

| GPU         | VRAM            | MSRP        |
| ----------- | --------------- | ----------- |
| RTX 5090    | 32 GB GDDR7     | \$1,999     |
| RTX 5080    | 16 GB GDDR7     | \$999       |
| RTX 5070 Ti | 16 GB GDDR7     | \$749       |
| RTX 5070    | 12 GB GDDR7     | \$549       |
| RTX 5060 Ti | 8 / 16 GB GDDR7 | \~$379–$499 |

### Consumer — GeForce RTX 40 series (Ada Lovelace, 2022–2024)

| GPU                   | VRAM         | MSRP      |
| --------------------- | ------------ | --------- |
| RTX 4090              | 24 GB GDDR6X | \$1,599   |
| RTX 4080 Super        | 16 GB GDDR6X | \$999     |
| RTX 4070 Ti Super     | 16 GB GDDR6X | \$799     |
| RTX 4070 Super / 4070 | 12 GB GDDR6X | \$599     |
| RTX 4060 Ti 16 GB     | 16 GB GDDR6  | \$499     |
| RTX 4060 Ti / 4060    | 8 GB GDDR6   | $299–$399 |

### Consumer — GeForce RTX 30 series (Ampere, 2020–2022)

| GPU                | VRAM         |
| ------------------ | ------------ |
| RTX 3090 Ti / 3090 | 24 GB GDDR6X |
| RTX 3080 Ti        | 12 GB GDDR6X |
| RTX 3080 12 GB     | 12 GB GDDR6X |
| RTX 3070 Ti / 3070 | 8 GB         |
| RTX 3060           | 12 GB GDDR6  |
| RTX 3060 Ti        | 8 GB GDDR6   |

<Tip>
  **Minimum for inference:** 8 GB VRAM (runs Qwen 1.5B–3B).\
  **Recommended for 7B–13B models:** 16–24 GB VRAM (RTX 3090 / 4090 / A5000).\
  **For 70B+ models:** 48–80+ GB or multi-node cluster (GB10, A100, H100, L40S, A40).\
  vLLM works best on Ampere (sm\_80) or newer. Turing (RTX 20-series) is supported with limitations.
</Tip>

***

## Live cluster demo

<img src="https://mintcdn.com/justme-8834e675-codex-docs-0-4-44/yQQjVu6VlAg0xzJZ/cluster-4node.gif?s=c15c89cce6d33da6c500f82981d2e86c" alt="AINode 4-node cluster — live topology with pulsing connections" style={{ borderRadius: '8px', border: '1px solid rgba(118,185,0,0.2)' }} width="1894" height="908" data-path="cluster-4node.gif" />

*Four GB10 nodes (3× DGX Spark + 1× ASUS GX10), 487 GB aggregated VRAM, automatic UDP discovery, live pulsing connections.*

***

## Architecture

AINode ships as a single unified container image. Every node in the cluster runs the same image.

```
ghcr.io/getainode/ainode:latest   ← pulled by the installer
         │
         ├── aiohttp web server (chat UI + API proxy, port 3000 / 8000)
         ├── federated master router (routes /v1/* by model name)
         ├── vLLM inference engine (one or more instances per node)
         ├── UDP discovery broadcaster (port 5679)
         └── training pipeline (LoRA / QLoRA / Full + quantization: AWQ / NVFP4)
```

No host Python venv. No source builds. Upgrade is `ainode update`.

***

## License

Apache 2.0. Free forever. Powered by [argentos.ai](https://argentos.ai).