alexlebens
a4dcf8515d
test-build / guarddog (push) Successful in 54s
test-build / build (push) Successful in 1m37s
release-image / guarddog (push) Successful in 42s
release-image / build (push) Successful in 1m16s
release-image / semantic-release (push) Successful in 35s
release-image / release-harbor (push) Has been skipped
release-image / release-gitea (push) Has been skipped
28 lines
817 B
Plaintext
28 lines
817 B
Plaintext
---
|
|
title: Ollama
|
|
description: Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
|
|
hero:
|
|
tagline: Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
|
|
image:
|
|
file: https://cdn.jsdelivr.net/gh/selfhst/icons@main/webp/ollama.webp
|
|
actions:
|
|
- text: Source
|
|
link: https://github.com/ollama/ollama
|
|
icon: right-arrow
|
|
- text: Deployment Chart
|
|
link: https://gitea.alexlebens.dev/alexlebens/infrastructure/src/branch/main/clusters/cl01tl/helm/ollama
|
|
icon: right-arrow
|
|
---
|
|
|
|
# Purpose
|
|
|
|
Local AI servers.
|
|
|
|
# Notes
|
|
|
|
[Open WebUI](https://github.com/open-webui/open-webui) frontend.
|
|
|
|
Configured mostly to run the Gemma models.
|
|
|
|
Tailscale connection to the desktop GPU for larger model processing.
|