# Local-only mode

> Keep a local model's work off the network: where data stays, what to bind, and how to verify from the logs and sockets.

Page: https://videotomd.com/b/text-local-only-mode/
Tool: Any AI · Tags: local-models, privacy, offline, ollama, lm-studio · 390 words, about 507 tokens
Pills: free · ran in Claude Code · ran in Ollama · self-check · done check · checked 2026-10-12 · Ollama · LM Studio · Jan · Open WebUI · Any text chat · Claude Code · chat only · always on · 7B ok · safety · ops

## Recipe

- Kind: instructions
- Stage: not set
- Loads: always on
- Works in: Ollama, LM Studio, Jan, Open WebUI, Any text chat, Claude Code
- Needs: chat only
- Bring: nothing
- Cost: free
- Model: 7B ok
- Tested in: Claude Code, Ollama
- Checked: 2026-10-12
- For: safety, ops

## When this is useful
- The documents you feed the model cannot leave the machine.
- You want to prove to yourself, not assume, that nothing is calling out.
- A teammate asks "is this actually offline?" and you want a two-line answer.


## Change it to
- Ollama: the block goes in a Modelfile `SYSTEM """..."""` with `PARAMETER num_ctx` set (the ollama row); see the Ollama Modelfile file for the full companion.
- LM Studio and Jan: paste the block into the system prompt field and save the preset or assistant (the lm-studio and jan rows).
- 7B model: keep the first two lines of the block; small models forget long conditions.
- Open WebUI: turn off web search for the model and put the block in its System Prompt (the open-webui row).


## If your AI needs to look something up
- It cannot, by design. You fetch https://docs.ollama.com/faq for the `OLLAMA_HOST` and log locations and paste what you need.


## Put it here

Always on: put it where your tool reads instructions every session:

- Ollama: Put the text in a Modelfile as SYSTEM """...""" with FROM <model> and PARAMETER num_ctx <n>, then `ollama create <name> -f Modelfile` and run <name>. Chat-only: paste it as the first message instead. Reload: ollama create again. Check it loaded: `ollama show --modelfile <name>` prints the SYSTEM; `ollama ps` shows the loaded context size. Source: https://docs.ollama.com/modelfile (checked 2026-10-12).
- LM Studio: Paste the text into the System Prompt field, set the context length, and save it as a preset so it survives a restart. Server: http://localhost:1234/v1. Reload: reload the preset. Check it loaded: the preset in the app; ask the model to repeat one rule. Source: https://lmstudio.ai/docs/app/presets (checked 2026-10-12).
- Jan: Settings → Assistants → instructions: paste the text and save. Reload: new thread. Check it loaded: Settings → Assistants; ask the model to repeat one rule. Source: https://jan.ai/docs/desktop/assistants (checked 2026-10-12).
- Open WebUI: Workspace → Models → your model → System Prompt: paste the text and save. Long reference goes in Knowledge and is retrieved, not always loaded. Reload: start a new chat. Check it loaded: the model's System Prompt field; ask the model to repeat one rule. Source: https://docs.openwebui.com/features/workspace/models (checked 2026-10-12).
- Any text chat: Paste the whole file as your first message, then your task. A chat cannot read files or run commands: it must hand you the command and wait for the output. Reload: paste it again in a new chat. Check it loaded: ask it to repeat one rule from the file; a general answer means it is not in context. Source: https://videotomd.com/use-with-your-ai/ (checked 2026-10-12).
- Claude Code: Save as CLAUDE.md in the project root, or .claude/CLAUDE.md. Other agents share the repo: put the shared rules in AGENTS.md and make CLAUDE.md one line, @AGENTS.md. Commit it. Start a new session: the file is read at launch. Reload: new session (or /memory to open the files). Check it loaded: /context lists the Memory files it read; /skills, /agents, /hooks list the rest; the InstructionsLoaded hook event fires once per loaded instruction file. Source: https://code.claude.com/docs/en/memory (checked 2026-10-12).

## Access

Membership: plans at https://videotomd.com/pricing/, or email then a plan at https://videotomd.com/b/text-local-only-mode/. A member's browser downloads the file there; an AI without that session needs the member to attach it.