this post was submitted on 18 Mar 2025
38 points (95.2% liked)

Selfhosted

60910 readers
1212 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

Detailed Rules Post

  1. Be civil.

  2. No spam.

  3. Posts are to be related to self-hosting.

  4. Don't duplicate the full text of your blog or readme if you're providing a link.

  5. Submission headline should match the article title.

  6. No trolling.

  7. Promotion posts require active participation, with an account that is at least 30 days old. F/LOSS without a paywall has exceptions, with requirements. See the rules link for details. Tags [CBH] or [AIP] are required, see the links in Rule 8 for details.

  8. AI-related discussions and AI-involved promotional posts have additional requirements for tagging, as noted in Rule 7 and the AI & Promotional Post Expanded Rules post, and find example disclosures here.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 3 years ago
MODERATORS
 

cross-posted from: https://lemmy.world/post/27013201

Ollama lets you download and run large language models (LLMs) on your device.

Install Ollama on Arch Linux

  1. Check whether your device has an AMD GPU, NVIDIA GPU, or no GPU. A GPU is recommended but not required.
  2. Open Console, type only one of the following commands and press return. This may ask for your password but not show you typing it.
sudo pacman -S ollama-rocm    # for AMD GPU
sudo pacman -S ollama-cuda    # for NVIDIA GPU
sudo pacman -S ollama         # for no GPU (for CPU)
  1. Enable the Ollama service [on-device and runs in the background] to start with your device and start it now.
sudo systemctl enable --now ollama

Test Ollama alone

  1. Open localhost:11434 in a web browser and you should see Ollama is running. This shows Ollama is installed and its service is running.
  2. Run ollama run deepseek-r1 in a console and ollama ps in another, to download and run the DeepSeek R1 model while seeing whether Ollama is using your slow CPU or fast GPU.

AMD GPU issue fix

https://lemmy.world/post/27088416

Use with Open WebUI

See this guide: https://lemmy.world/post/28493612

top 2 comments
sorted by: hot top controversial new old
[โ€“] mierdabird@lemmy.dbzer0.com 3 points 1 year ago (1 children)

Additionally here's an excellent tutorial to do it via Docker Compose in Cosmos Cloud:

https://discord.com/channels/1083875833824944188/1283413252356706416/1283785229923909694

  1. Locate the Docker Compose File:

    • Find the Docker Compose file for the desired service. For example, you can use the Open Chat UI and Ollama setup from the following GitHub repository: Open Chat UI Docker Compose File
  2. Docker Compose Configuration:

  3. Import the Docker Compose File:

    • Go to the ServApps section in Cosmos.
    • Click on Import Compose File.
    • Click Next and proceed to add or modify the configuration. Replace any ${} placeholders with the desired values, such as latest or any specific version you prefer. You can also make changes later if needed.
  4. Create the Docker Containers:

    • Click Create. The Docker containers will be automatically created based on the provided configuration.
  5. Access the Service:

    • After the containers are created, you can access the service by adding a new URL.
    • Cosmos typically auto-detects the correct port, so you usually only need to create the URL.
    • You can now access the service as usual.
  6. Customize with Labels:

    • Optionally, you can customize the service further using labels such as:
      • cosmos-icon
      • cosmos-stack
      • cosmos-stack-main
  7. Modify Environment Variables:

    • Refer to the documentation for the Docker service and its environment variables. You can modify these variables directly from the Docker or Compose tab in Cosmos.

That's it!

[โ€“] autonomoususer@lemmy.world 3 points 1 year ago* (last edited 1 year ago)

Cosmos Cloud fails to include a libre software license text file. We do not control it, anti-libre software. This defeats the purpose of running Ollama, libre software, on our own device.

Also, although Docker on Arch Linux is fine, Docker Desktop used to install Docker on Windows is also anti-libre software. The upcoming guide will provide a workaround. Of course, Windows is anti-libre software, so this is for harm reduction at best.

However, thank you for freeing this information from Discord, also anti-libre software.