# 📱 Free PrivateLM — one big AI across your phones, no cloud

**URL:** <https://onehack.st/t/free-privatelm-one-big-ai-across-your-phones-no-cloud/327429>\
**Category:** Tools & Scripts\
**Tags:** privacy, android, ai\
**Created:** [November 22, 2026, 11:27am UTC](https://onehack.st/t/free-privatelm-one-big-ai-across-your-phones-no-cloud/327429 "2026-11-22T11:27:55Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![TheStrength](https://onehack.st/user_avatar/onehack.st/thestrength/32/46753_2.png) [@TheStrength](https://onehack.st/u/TheStrength)\
**Post date:** [November 22, 2026, 11:27am UTC](https://onehack.st/t/free-privatelm-one-big-ai-across-your-phones-no-cloud/327429/1 "2026-11-22T11:27:55Z")

</div>

![Phones as Wireless GPU](https://onehack.st/uploads/default/original/3X/f/0/f0529f9553a8f99a3df4000ad864c37b071f3cde.jpeg)

### THE PHONES IN YOUR DRAWER JUST BECAME ONE BRAIN

One GGUF model, split across phones you already own. Your laptop chats with it like any other AI.

📱 **Your strongest Android leads** — it loads the model and runs the chat.

🔗 **The rest join by QR** — another Android, an iPhone, an iPad.

💻 **Your PC uses one link** — `http://192.168.x.y:8080/v1`.

🎁 **Free and MIT, nothing new to buy** — [github.com/orailnoor/cross-platform-llm-client](https://github.com/orailnoor/cross-platform-llm-client/releases/tag/1.0.7-cluster)

🧠 **Brains that split well** — pick by small active slice, not by size:

- **26B-A4B · 10 GB** — the four-phone demo brain
- **30B-A3B · 10 GB** — the coding-flavoured one
- **16B-A3B · 6.5 GB** — for the smaller phones in the pile

> **🔌 Plug the cluster into apps you already use**
>
> - [Open WebUI](https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible/) — add a connection with the `/v1` URL and the app’s `aichat_…` key
> - [Continue for VS Code](https://docs.continue.dev/customize/model-providers/top-level/openai) — coding with the brain living on your phones
> - [AnythingLLM](https://docs.anythingllm.com/setup/llm-configuration/cloud/openai-generic) — chat with your own files; base path includes `/v1`
> - [ChatBox](https://github.com/chatboxai/chatbox-docs/blob/main/guides/providers/README.md) — a small desktop chat window
> - [LobeChat](https://aitokensai.com/guides/lobechat-openai-compatible/) — set `OPENAI_PROXY_URL` to the `/v1` URL
> - [Obsidian Text Generator](https://github.com/nhaouari/obsidian-textgenerator-plugin/) — ask your notes on the private brain

> **🧩 The trick that makes it click**
>
> - 🧠 **Small active slice wins** — a 26B brain wakes about 4B per word, so each phone reads a sliver: [the demo brain](https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF) · [the coding one](https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF) · [the lighter one](https://huggingface.co/mmnga/Moonlight-16B-A3B-Instruct-gguf)
> - 📏 [whichquant](https://github.com/ngo-binh0108/whichquant) checks the fit from the model’s header before you download
> - 🌐 [Pooled](https://github.com/Nehanth/pooled) runs the same pooling in browser tabs — no install, iPhones join as equals
> - 🛡 [Tailscale](https://tailscale.com/) on the leader and laptop reaches the cluster from anywhere
> - 🎨 The app also draws images offline and reads photos and PDFs with a vision brain
> - 🧵 [The maker’s walkthrough](https://www.youtube.com/watch?v=reOeczuEzOA) shows the QR pairing end to end

Your drawer just got a new job. 🧩
