All how-tos
How to install.
20 step-by-step install guides for local LLM tools, models and runtimes.
◆ The BestLLMfor kits — the reference guide by use case · $24 the kit · $49 all, lifetime →
How to Use Aider with Ollama as a Local Copilot
How to Add a Local LLM to Claude Desktop via MCP
How to Wire Continue.dev to a Local Ollama LLM in VS Code
How to Use a Local Ollama LLM as Cursor's Backend
How to Install DeepSeek R1 32B on RTX 5090
How to Wire LangChain to a Local LLM — Production-Ready
How to Use LiteLLM Router with Ollama — OpenAI-Drop-In
How to Build llama.cpp from Source with CUDA — 2026 Guide
How to Build llama.cpp with Metal on Mac M-Series
How to Install Llama 3.3 70B on RTX 4090 — Step-by-Step
How to Use LlamaIndex with a Local Ollama LLM
How to Install Mistral Small 3.1 24B on RTX 3060
How to Run Llama on Apple Silicon with MLX — Native Performance
How to Install Ollama with ROCm on AMD GPU
How to Install Ollama on Windows 11 with WSL2 — Full Guide
How to Self-Host OpenWebUI in Docker — 5-Minute Setup
How to Install Qwen 2.5 Coder 32B on Mac M4 Max
How to Self-Host TabbyAPI as an OpenAI-Compatible Endpoint
How to Install text-generation-webui with CUDA on Windows
How to Run vLLM in Docker with NVIDIA CUDA — 10-Minute Setup