AI How-To Guides
Step-by-step tutorials for running AI tools locally, self-hosting automation, and deploying on a VPS. Every guide includes working code, real commands, and troubleshooting.
Local AI
20 guidesHow to Use Ollama with Python: API Integration Tutorial (2026)
Learn how to use Ollama with Python using the official ollama library and the REST API. Covers streaming, chat...
How to Run Nemotron 3 Ultra on Ollama (2026 Cloud Guide)
Nemotron 3 Ultra is cloud-only on Ollama, a 550B-parameter MoE model. Sign in, run nemotron-3-ultra:cloud, set...
How to Run DeepSeek OCR on Ollama: Local Setup Guide (2026)
DeepSeek OCR runs locally on Ollama as a 3B vision model using optical context compression. Install it, run it...
How to Run Mistral Medium 3.5 Locally with Ollama (2026 Guide)
Mistral Medium 3.5 is a 128B dense model with vision and 256K context. Install Ollama, pull the right quant ta...
How to Run Laguna XS 2.1 on Ollama: Local Setup Guide (2026)
Poolside's Laguna XS 2.1 is a 33B MoE coding model with real local Ollama tags. Compare q4_K_M, q8_0, and bf16...
How to Run DeepSeek R1 Locally with Ollama (2026 Guide)
Run DeepSeek R1 locally using Ollama on Linux, macOS, or a VPS. Model size comparison, RAM requirements, and s...
Best Local LLM Models to Run in 2026 (Benchmarks + Use Cases)
The best local LLM models to run on your own hardware in 2026. Covers Llama 3.3, Mistral, Qwen 2.5, Phi-4, Dee...
How to Run Stable Diffusion Locally: ComfyUI and AUTOMATIC1111 Guide
Run Stable Diffusion locally with ComfyUI or AUTOMATIC1111. Complete setup guide for Windows, Linux, and macOS...
How to Run GLM 5.2 on Ollama: Cloud Setup Guide (2026)
GLM 5.2 isn't a local Ollama pull. It's Z.ai's 744B-parameter cloud model. Learn to run glm-5.2:cloud, set up ...
How to Run Ornith 1.0 on Ollama: Local Setup Guide (2026)
Ornith 1.0 is DeepReinforce's MIT-licensed model that learns to write its own coding scaffolds. Pull ornith:9b...
How to Set Up a Self-Hosted Perplexity Alternative with Perplexica
Install Perplexica with Docker Compose: a self-hosted Perplexity alternative using SearXNG and Ollama. Free, p...
How to Run MedGemma on Ollama: Local Setup Guide (2026)
MedGemma is Google's medical AI model built on Gemma 3. Run medgemma:4b or 27b locally with Ollama, send medic...
How to Run Gemma 4 on Ollama: Complete Setup Guide (2026)
Run Google's Gemma 4 locally with Ollama. Compare the E2B, E4B, 12B, 26B, and 31B sizes, check RAM and VRAM ne...
How to Run MiniMax M3 on Ollama: Cloud Setup Guide (2026)
MiniMax M3 is cloud-only on Ollama, a 428B-parameter MoE coding model with 1M context. Run minimax-m3:cloud, s...
How to Run Ollama Locally: Complete Setup Guide (2026)
Step-by-step guide to install Ollama on Linux, macOS, or Windows, pull your first model, and access the REST A...
How to Set Up Open-WebUI with Ollama (Docker Guide)
Install Open-WebUI for a ChatGPT-style interface with local Ollama models. Covers Docker setup, Docker Compose...
Best Open-Source AI Coding Assistants in 2026: Compared and Ranked
Continue.dev, Aider, Tabby, Cody, and more: the 6 best free GitHub Copilot alternatives compared by setup, mod...
How to Install ComfyUI with Docker (2026 Setup Guide)
Install ComfyUI with Docker in minutes. Step-by-step guide: Docker run, Docker Compose, model downloads, custo...
How to Set Up AnythingLLM with Ollama (2026 Guide)
Install AnythingLLM Desktop or Docker, connect Ollama, and set up a local RAG workspace. Covers Ollama URL fix...
How to Run Kimi K2 on Ollama: Cloud Setup Guide (2026)
Kimi K2 isn't a local Ollama pull. Run kimi-k2.6:cloud for general use, kimi-k2.7-code:cloud for agentic codin...
Automation
3 guidesHow to Install n8n with Docker Compose (Self-Hosted Setup)
Step-by-step guide to self-host n8n with Docker Compose, configure a PostgreSQL database, set up Nginx reverse...
n8n AI Workflow Examples: 5 Practical Automations to Build in 2026
Five practical n8n AI workflows you can build today: AI email responder, web scraper, chatbot with memory, doc...
How to Run a Local LLM with Home Assistant (Ollama Setup, 2026)
Connect Ollama to Home Assistant for private, offline smart home control. Step-by-step Assist pipeline setup, ...
Docker & VPS
2 guidesHow to Set Up LiteLLM Proxy with Docker (2026)
Set up LiteLLM proxy with Docker to use 100+ LLMs via a single OpenAI-compatible API. Covers config file, virt...
How to Deploy n8n on a VPS: Production Setup with Nginx and SSL (2026)
Deploy n8n on a VPS with Nginx reverse proxy, free SSL certificate, and PostgreSQL. Full production setup guid...
AI Agents
6 guidesHow to Set Up Claude MCP Servers: Complete Configuration Guide (2026)
Set up Model Context Protocol servers with Claude Desktop. Configure filesystem, web search, PostgreSQL, GitHu...
How to Install Hermes Agent with Ollama Local Models (2026)
Connect Hermes Agent by Nous Research to Ollama local models. Step-by-step install, 64K context fix, SOUL.md s...
How to Install Flowise with Docker: AI Agent Builder Setup Guide
Step-by-step guide to install Flowise AI agent builder with Docker. Set up LLM chains, chatbots, and autonomou...
How to Build an AI Agent with n8n (2026 Guide)
Build a working AI agent in n8n using the AI Agent node, memory, tools, and custom logic. Covers OpenAI, Ollam...
How to Run OpenClaw with Ollama Local Models (2026 Guide)
Connect OpenClaw AI agent to Ollama local models. Step-by-step Docker setup, Ollama configuration, and model s...
How to Install Hermes Agent with LM Studio (2026)
Set up Hermes Agent with LM Studio as the local inference backend. Covers model loading, 64K context config, p...
Comparisons
2 guidesOllama vs LM Studio: Which Local LLM Tool Should You Use in 2026?
Ollama vs LM Studio compared on ease of use, model support, API access, performance, and use cases. Find out w...
Flowise vs Langflow: Which AI Builder Should You Use in 2026?
Flowise vs Langflow compared: installation, features, integrations, performance, and which tool fits each use ...
Need a Server for These Guides?
Most of these guides run great on a Contabo VPS. Plans start at €5.45/mo with NVMe storage, 4 vCPUs, and a Linux environment ready to go.
View Contabo VPS Plans