AI-handledningar

Build a Streamlit benchmark application that tests whether Opus 4.7 self-critique memory actually improves coding performance across high, xhigh, and max effort levels.

Learn how to pair Claude Code Auto Mode with Telegram Channels to run an autonomous write-test-debug loop from your phone.

Learn how to fine-tune Qwen3.6 on an H100 NVL GPU using SFT, from dataset preparation and 4-bit loading to training and evaluation.

Learn how to build an automated LLM-as-a-judge system to evaluate your RAG pipelines for faithfulness and relevance at scale and bridge the gap in AI testing.

Learn the capabilities of Anthropic’s best publicly available model, Claude Opus 4.7, and build a data science tool that can turn a chart into raw data.

In this guide, we will rent an H200 GPU and install llama.cpp, download MiniMax M2.7 GGUF, run it locally, test it in the WebUI, and connect it to OpenCode.

Master the Ollama Python SDK for local LLM development. Learn to generate text, handle multi-turn chats, use vision models, and build AI apps securely.

Build a working demo app that calls all three Microsoft MAI models via Azure speech-to-text, text-to-speech, and image generation, and learn what these models can do.

Discover how to install and run LLMs locally using LM Studio. Keep your data private, chat with documents using built-in RAG, and set up a local API.

Learn how to set up Claude Code inside Cursor, understand the difference between Claude Code and Claude models in Cursor, and decide when each workflow makes sense for your project.

Learn how to run PrismML's fast and efficient 1-bit Bonsai model locally on Windows, from download and setup to WebUI testing, reaching 88.6 tokens per second.

Learn how to install and use the Claude Code VS Code extension, what it can do across your codebase, and how it compares to working from the terminal.