OpenCode is the open-source coding agent that has taken off this year: about 214,000 stars on GitHub, MIT-licensed, and a new release most weeks. It runs in your terminal, reads your project, edits files and runs commands. By default it talks to cloud models, but it can just as easily use a model running on your own machine through Ollama, LM Studio or llama.cpp. Getting that … [Read more...] about OpenCode With a Local LLM: Ollama, LM Studio and llama.cpp Setup
Mac mini M6 for Local AI: Which Configuration to Buy, and Why 16GB Is Slower
The 2026 Mac mini comes with an M6 or an M5 Pro chip, and Apple pitches both at local AI. Its product page says a Neural Accelerator in each GPU core "speeds up tasks like running on-device AI models", and it names Ollama and LM Studio Bionic among the apps it is built for. If you want a small, quiet box for running language models at home, it is the obvious candidate. The … [Read more...] about Mac mini M6 for Local AI: Which Configuration to Buy, and Why 16GB Is Slower
llmfit: How the Local LLM Fit Checker Works, and How Far to Trust It
llmfit answers the first question everyone asks about local AI: which models will actually run on this machine? It is a free, MIT-licensed command-line tool that detects your CPU, RAM and GPU, then ranks hundreds of open models by how well they fit and how fast they should run. It has nearly 38,000 stars on GitHub and has shipped a new release every week or two since August. … [Read more...] about llmfit: How the Local LLM Fit Checker Works, and How Far to Trust It
Flux LoRA in 2026: Which Base Model You Can Legally Train On
Quick answer A Flux LoRA is a “Derivative” under Black Forest Labs’ licence, and the licence says so in as many words: a Derivative includes any “customized or fine-tuned version” of the model. Train on a [dev] model and the LoRA inherits the non-commercial restriction. The images are a separate matter. Outputs are explicitly not Derivatives, and you “may use Output for … [Read more...] about Flux LoRA in 2026: Which Base Model You Can Legally Train On
Five Ways a Real-World PDF Breaks pdftotext (And How to Read It Anyway)
Every tutorial on extracting tables from PDFs uses the same example: a clean, machine-generated invoice where pdftotext -layout returns tidy columns and everyone goes home happy. Then you point the same script at a document somebody actually made, in InDesign or Illustrator, for print — and it returns rows of blanks. Or worse, rows that look correct and aren't. I spent a few … [Read more...] about Five Ways a Real-World PDF Breaks pdftotext (And How to Read It Anyway)
LLM Context Windows Explained: What They Cost You in VRAM
Every model page advertises a context window — 8K, 128K, a million tokens. It reads like a feature you either have or don't. Locally it is not a feature at all: it is memory you pay for, every token of it, and on a long context the bill can exceed the model itself. This guide explains what the context window is, the arithmetic that decides what it costs you, and the three … [Read more...] about LLM Context Windows Explained: What They Cost You in VRAM
DeepSeek API Pricing vs Running It Locally: The Break-Even Point
DeepSeek is unusual: it publishes an API and releases the weights of the models behind it under a permissive licence. That raises an obvious question — if you can download it, should you run it yourself instead of paying per token? This guide gives the current API prices, the real hardware those same models need, and the arithmetic that decides it. The honest answer surprises … [Read more...] about DeepSeek API Pricing vs Running It Locally: The Break-Even Point
Local OCR with Ollama: Reading Documents Without the Cloud
Sending a scanned contract, an invoice or a passport photo to a cloud OCR service means uploading the document. The same reasoning carries to the next step: once the text is out, local text-to-speech can read it aloud without the document leaving the machine either. A local vision model avoids that entirely: the image never leaves your machine. This guide covers how to read … [Read more...] about Local OCR with Ollama: Reading Documents Without the Cloud
How to Use Ollama with LangChain in Python (2026)
LangChain is the usual way to put a local model behind real application code — chains, retrieval, tool calls — and Ollama is the easiest way to serve that model. This guide covers the current integration package, a working example of each of the two things you will actually use (chat and embeddings), and the settings that cause most of the trouble. Quick answer Install one … [Read more...] about How to Use Ollama with LangChain in Python (2026)
Stable Diffusion Checkpoints, LoRAs and VAEs Explained (2026)
Download anything for Stable Diffusion and you hit the same wall: the file is called a checkpoint, or a LoRA, or a VAE, and nothing tells you which folder it goes in or why your image looks washed out without it. This guide explains what each file type actually is, how big each one is, where it goes, and why the file extension matters more than most tutorials admit. Quick … [Read more...] about Stable Diffusion Checkpoints, LoRAs and VAEs Explained (2026)