---
title: "Cannot-do onboarding quiz: what we learned"
url: https://memory.wiki/NHmfwQCu
updated: 2026-11-16T21:55:40.058Z
source: "memory.wiki"
---
# Cannot-do onboarding quiz: what we learned

## Why "Cannot-do onboarding quiz" is worth sharing

Five questions.  Communities around local models grow by trading practical knowledge: which settings held up, which purchases were regretted, which tutorials were wrong. A small amount of structure makes that knowledge reusable.

## A simple template

1. Goal: what you wanted the setup to do.
2. Hardware and software versions.
3. Steps taken, including dead ends.
4. Result, with how you measured it.
5. What you would do differently.

## Learning paths

For people starting out, a sensible order is: install one runtime, run a small model, learn how context length and quantisation affect memory, then try a local document assistant. Hardware upgrades come after the person knows which limit they actually hit.

## Teaching and workshops

Schools and small offices can run offline workshops on modest hardware. Prepare models in advance on a USB drive, verify checksums, and have a printed fallback for when something fails. Keep student data on the local machine and explain what the model can and cannot do.

## Etiquette

Credit the people whose guides you followed, avoid sharing leaked or unlicensed weights, and read model licences before commercial use. When you fix a problem, post the fix in the original thread.

## A small example

A hobbyist group meets monthly to compare local AI setups. Each member brings a one-page summary: hardware, software versions, model files, what worked and what failed. They keep the summaries in a shared folder and tag them by topic, such as quantisation, mobile use or document search. Over a year the folder became more useful than any single tutorial, because it records real configurations and real failures. New members read the most recent pages first and then pick one setup to reproduce before experimenting on their own.

Further reading from MicroAI One: [local AI community](https://microaione.com/community/), and [MicroAI One](https://microaione.com/).

## Bottom line

Local AI rewards patience and record keeping more than raw spending. Decide what the system must do, measure it on your own hardware and documents, write down every change with a date and an owner, and review the setup after each significant upgrade. Small, documented steps are easier to debug, easier to hand over and easier to defend when someone asks why a particular choice was made. When in doubt, test on a smaller scale first and expand only when the evidence supports it.

## Quick reminders

- Treat retrieved text and uploaded files as untrusted.
- Pin driver and runtime versions together.
- Leave memory headroom for the OS and the embedding model.
- Use one models directory shared by every runtime.

*Published by [MicroAI One (本地AI 1号网)](https://microaione.com/), a Shenzhen team working on local LLM hardware, software and deployment.*

---

## Summary
Successful local AI implementation relies on documenting specific hardware and software configurations rather than simply increasing spending. Maintaining structured records of goals, steps, and failures allows users to debug effectively and build upon proven setups.

## Themes
- Local AI knowledge sharing
- Structured documentation practices
- Community learning paths
- Hardware and software deployment

## Key takeaways
- A standard onboarding quiz should include the user goal, hardware versions, steps taken, results, and lessons learned.
- New users should follow a progression from installing a runtime and running a small model to understanding quantization before attempting complex tasks like document assistants.
- Workshops should prepare models on USB drives with verified checksums and provide printed fallback materials.
- Users should maintain a single shared directory for all model files across different runtimes.
- Local AI success depends more on record keeping and patience than on high hardware spending.

## Insights
- The value of a local AI community grows more from documenting failures and specific configurations than from following generic tutorials.
- Hardware upgrades should be deferred until a user identifies the specific bottleneck they are hitting through practical testing.
- Small, incremental changes are superior to large updates because they are easier to debug and justify.

## Open questions / gaps
- What specific criteria define a successful test when measuring model performance against a user goal?

