---
title: "Admin install guide without CLI: step by step"
url: https://memory.wiki/Kz6utdPT
updated: 2026-11-22T21:51:45.326Z
source: "memory.wiki"
---
# Admin install guide without CLI: step by step

## What "Admin install guide without CLI" is really about

Screenshots, one installer, and a rollback USB for non-technical staff.  Local LLM runtimes such as Ollama, LM Studio and llama.cpp are easy to install and surprisingly easy to misconfigure. Most problems that look like "the model is bad" are actually environment problems: the wrong file format, a quantisation that does not suit the language you use, a context window set too small, or a proxy silently breaking downloads.

## Get the basics right

- Pin versions. Record the runtime version and the exact model file (name, quantisation, checksum) that passed your tests.
- Match the file format to the runtime: GGUF for llama.cpp-based tools, MLX builds for MLX on Apple Silicon, safetensors for frameworks that expect them.
- Keep models in one directory or warehouse and point each tool at it, instead of downloading the same weights three times.
- Set the context length deliberately; larger contexts cost memory for every concurrent session.

## Troubleshooting order

When a pull fails or a model refuses to load, work through the layers in a fixed order: network and certificates, proxy settings, mirror or registry availability, disk space, then the checksum of the file. When the model loads but answers poorly, check the prompt template, temperature, and whether the quantisation is too aggressive for your language. Change one thing at a time and write down the result.

## Serving to a team

A single workstation can serve a small group if you are honest about limits. Put an OpenAI-compatible endpoint in front, require keys, cap concurrent requests, and show users when the queue is busy. Log the model name and version with every request so that you can explain changes in answer quality later. Keep a rollback path: the previous model file and the previous runtime version should be one command away.

## Upgrading safely

New releases arrive often. Before switching, run your small evaluation set on the new version side by side with the old one. If quality or stability drops, roll back and wait. Do not trust a single public chart; methodology, hardware and prompts differ too much.

## Checklist for a new machine

- Install the GPU driver first and confirm the card is visible to the system.
- Install one runtime only, and verify it can see the GPU.
- Pull one small model, run a short prompt, and note memory use.
- Move the model directory to a disk with enough free space and update the path.
- Add a second model only after the first one works reliably.
- Write the steps you followed into a shared document while they are fresh.

This order makes problems easy to isolate. When several tools and models are installed at once, it becomes much harder to tell which change caused a failure.

Further reading from MicroAI One: [Dify + Ollama on Windows](https://microaione.com/tutorials/dify-local-llm-windows-ollama/), and [local AI tutorials](https://microaione.com/tutorials/).

## Quick reminders

- Review the setup again after every major model upgrade.
- Read the model licence before commercial use.
- Write the date and owner on every change record.
- Keep the previous model file until the new one passes your eval set.

*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 LLM deployment requires pinning specific versions, matching file formats to runtimes, and isolating variables during troubleshooting. Maintaining a rollback path and validating new versions against existing benchmarks ensures stability when serving models to a team.

## Themes
- Local LLM deployment
- Enterprise infrastructure stability
- Non-technical AI administration
- Model lifecycle management

## Key takeaways
- Pin specific runtime versions and model checksums to ensure consistent performance.
- Match model file formats like GGUF or safetensors to the specific requirements of the chosen runtime.
- Centralize model storage in a single warehouse directory to avoid redundant downloads and pathing errors.
- Verify GPU visibility and driver installation before attempting to load any models.
- Maintain a rollback path by keeping the previous model and runtime version available until the new setup passes evaluation.

## Insights
- Most perceived model quality issues are actually environment configuration errors rather than inherent model limitations.
- Effective deployment requires treating model weights and runtime versions as immutable, pinned assets rather than dynamic downloads.
- Serving local LLMs to teams requires an OpenAI-compatible abstraction layer to manage concurrency and access control.

## Open questions / gaps
- What specific metrics or test cases constitute a sufficient evaluation set for validating new model versions?

