Guides

How to use Gemma 4 with OpenClaw

Set up OpenClaw with Google's Gemma 4 locally via Ollama for a private, fully local AI assistant.

April 15, 2026

How to Use LM Studio with OpenCode

Use OpenCode with LM Studio as a local coding agent in your terminal.

April 15, 2026

How to run Gemma 4 locally

A step-by-step guide to running Google's Gemma 4 language model locally using Ollama, with text, audio, and image input support.

April 2, 2026

Bonsai 1-bit: An 8B LLM that fits in 1 GB

PrismML just shipped a true 1-bit LLM that fits 8 billion parameters into 1.15 GB. Here's why it's such a big deal.

April 2, 2026

Cheapest GPU Cloud Providers Compared

Which cloud provider offers the cheapest GPU pricing? This guide compares on-demand GPU cloud prices across 48+ providers, normalized to a per-GPU-per-hour rate for fair comparison.

March 3, 2026

Coolify vs. Dokploy: Which is best in 2026?

A detailed comparison of Coolify and Dokploy, two open-source tools that give you a Heroku-like experience on your own VPS.

January 25, 2026

Run LLMs Locally on Mac with LM Studio

A step-by-step guide to running open-source LLMs on your Mac using LM Studio and Apple's MLX framework for GPU acceleration.

November 11, 2025

How to run Mistral locally

A step-by-step guide to running Mistral AI models locally using Ollama, from the tiny Ministral 3B to the capable Mistral Small 3.2.

July 18, 2025

How to run Gemma 3 locally

A step-by-step guide to running Google's powerful and lightweight Gemma 3 language model locally using Ollama.

July 18, 2025

Serverless GPUs: 4 Cloud Providers Compared

A comparison of four serverless GPU providers - Replicate, Fal.ai, Koyeb, and Runpod - for deploying AI models without managing infrastructure.

June 11, 2025

Install DeepSeek R1 Locally or Self-Host It

In this guide, I'll show you how to run DeepSeek R1 locally on your machine (no GPU required), and how to deploy it to a cloud server.

January 28, 2025

8 Best Vercel Alternatives for Production

Vercel is great for deploying web apps, but it's not always the best fit. In this guide, I explore eight alternatives for different use cases, from self-hosting to managed platforms.

December 11, 2024

Vector Databases Explained Simply

Vector databases are quite popular right now, especially for building recommendation systems, adding context to chatbots and LLMs, or comparing content based on similarity. In this guide, I'll explain what vector databases are, how they work, and when to use them.

November 26, 2024

Running Llama 3 Locally

In this guide, I'll show you how to run Llama 3 locally on your machine (no GPU required).

October 2, 2024

Securing an Ubuntu Server: A Practical Guide

In this guide, I describe how to secure an Ubuntu server with best practices, including setting up a firewall, disabling password authentication, and enabling automatic security updates.

September 9, 2024

Self-Host Next.js with Kamal and GitHub Actions

In this guide, I show you how to deploy a Next.js app to your own server, with automated SSL certificates, caching, and CI/CD using GitHub Actions.

September 4, 2024