Install LM Studio Windows - stone-alex/EliteIntel GitHub Wiki

🪟 Local LLM - Windows Setup (LM Studio)

Running a local LLM keeps everything private, offline, and free (beyond electricity and hardware). Think of it as the difference between running a game on your own rig vs. streaming it from the cloud - lower latency, no subscriptions, no one snooping on your loadout.

LM Studio is an alternative to Ollama. It uses the same models and serves the same OpenAI-compatible API that Elite Intel talks to. Pick whichever you prefer - you can even switch between them in settings.

It requires LM Studio and a capable GPU.

Minimum Hardware

To run Elite Dangerous and the LLM on the same machine, you need at minimum an NVIDIA RTX 3060 with 24 GB VRAM.

Tip: You can point Elite Intel at an LM Studio instance running on a separate PC on your network. If you have a home lab or a spare box with a good GPU, that's a great option - the game PC doesn't carry the load at all.

Recommended Model

Model VRAM Required Notes
tulu-3.1-8b-supernova Q4_K_M ~5 GB ✅ Recommended. Fast, accurate, works great for commands and queries.
tulu-3.1-8b-supernova Q8_0 ~8.5 GB Higher quality, if you have the VRAM headroom.
qwen3 8B ~8 GB Experimental. Expect occasional missed commands and hallucinations.

Step 1 - Install LM Studio

Open PowerShell and run:

irm https://lmstudio.ai/install.ps1 | iex

This installs the lms CLI and the LM Studio runtime. Open a new PowerShell window after it finishes for the changes to take effect.

Verify it worked:

lms --help

Note: If you already have the LM Studio desktop app installed, the lms CLI comes bundled with it - you may already have it. Try lms --help first before running the install script.

Step 2 - Download the Model

lms get matrixportalx/Tulu-3.1-8B-SuperNova-Q4_K_M-GGUF

or

lms get Tulu-3.1

and choose the matrixportalx/Tulu-3.1-8B-SuperNova-Q4_K_M-GGUF variant (Could be listed as Tulu-3.1-8B-SuperNova-Q4_K_M-GGUF)

To see all models you've downloaded:

lms ls

Step 3 - Start the Server

Load the model and start the inference server:

lms load tulu-3.1-8b-supernova --context-length 8192 --gpu max
lms server start

NOTE the --context-length 8192 flag is important. Without it, you may end up with a small context window, and it will cut off part of the prompt which will lead to failures and hallucinations!

Verify it's running - open a browser or another PowerShell window and hit:

http://localhost:1234/v1/models

You should get back a JSON list of loaded models. The model ID string in that response is what you'll put in Elite Intel's LLM Model field.

To stop the server:

lms server stop

⚠️ Important: The LM Studio server does not survive reboots. You need to run lms server start again after each restart, or use one of the auto-start options below.

Step 4 - (Optional) Auto-Start on Boot

There are two ways to keep the server running across reboots.

Option A - Desktop App (Easiest)

If you have the LM Studio desktop app installed, this is the simplest path:

  1. Open LM Studio and press Ctrl + , to open Settings.
  2. Check "Run LLM server on login".
  3. From now on, closing the app minimizes it to the system tray and keeps the server running. It restores automatically on next login.

Option B - Task Scheduler (Headless / No GUI)

  1. Press Win + R, type taskschd.msc, press Enter.
  2. Click Create Task in the right panel.
  3. General tab: Name it LM Studio Server. Check "Run with highest privileges".
  4. Triggers tab: Click New → "At log on" → OK.
  5. Actions tab: Click New → "Start a program".
    • Program/script: %USERPROFILE%\.lmstudio\bin\lms.exe
    • Add arguments: server start

To also load the model automatically, create a batch file instead:

@echo off
%USERPROFILE%\.lmstudio\bin\lms.exe daemon up
%USERPROFILE%\.lmstudio\bin\lms.exe load tulu-3.1-8b-supernova --yes --context-length 8192 --gpu max
%USERPROFILE%\.lmstudio\bin\lms.exe server start

Save it as start-lmstudio.bat somewhere permanent (e.g. C:\Scripts\) and point the Task Scheduler Action at that file.

Step 5 - Wire It Up in Elite Intel

Head to the Settings tab in Elite Intel:

  • Leave the LLM Key field blank (local LM Studio doesn't need one).
  • LLM Address - set to http://localhost:1234/v1/chat/completions. If LM Studio is on another machine, replace localhost with that machine's IP.
  • LLM Model - paste in the model ID string from http://localhost:1234/v1/models.
  • Command LLM - set to the same model ID.
  • Query LLM - set to the same model ID.
  • Hit Stop → Start on the AI tab to apply changes.

Community 👉Matrix👈