IT Expert Blog — since 2017

Practical knowledge on AI and technology for every IT Pro

Articles on local AI models, Python programming, developer tools and IT project management. No fluff — just what works in practice.

Browse Articles 🤖 AI Category

50+ articles

11 categories

2017 since

Artur Poniedziałek

IT Expert & Project Manager

AI enthusiast, local LLMs and practical tech solutions. Managing IT projects and sharing experience on this blog.

🤖 AI in Practice ⚡ IT Management 🐍 Python 🖥️ Local LLMs

🤖 AI 🐍 Python 🧠 Machine Learning 🗄️ Databases 🔧 Tools 🐘 PHP Laravel 🎮 Games 🖨️ 3D Printing

Latest Articles

Latest

🤖 AI

Qwen3.6-35B-A3B in practice: text, image, video and local API workflows

A practical guide to Qwen3.6-35B-A3B as one local multimodal model. See how to design prompts, call LM Studio or Ollama endpoints, and analyze images or sampled video frames with three focused scripts.

7th June 2026 17 min

Read article

🤖 AI

30th May 2026 10 min

Benchmark lab for local models: real 27B-35B results on one 48 GB GPU

A practical benchmark lab for local models on AMD PRO W7900 48 GB. Real tok/s, TTFT, disk size, VRAM after loading and…

Multi-Token Prediction on AMD W7900: 1.85× speedup with llama-server Vulkan (Qwen3.6-35B benchmark)

We benchmark Multi-Token Prediction in llama-server (llama.cpp, Vulkan) on AMD PRO W7900. Real results: 49.7 → 91.8 tok/s, up to 2× on…

Private AI Assistant for Productivity: How Freelancers and Managers Can Get Work Done in the Background

A practical English article on private AI assistants, background work, personal context, privacy, and real productivity gains for freelancers and managers.

Describing PDF Charts with Vision Language Models

Use Vision Language Models (VLMs) to convert PDF charts into searchable text descriptions. Build complete pipelines for chart extraction, processing, and RAG…

Running Local LLMs with OpenAI-Compatible APIs

Run powerful LLMs locally using OpenAI-compatible APIs. Learn to set up LM Studio, Ollama, and vLLM servers for private, cost-free AI inference.

Hybrid Search: Combining Vector and Keyword Retrieval

Master hybrid search combining vector similarity and keyword matching. Learn BM25, Reciprocal Rank Fusion, and score merging strategies for optimal RAG retrieva

LanceDB: Lightweight Vector Database for AI Applications

Complete guide to LanceDB, a lightweight serverless vector database for AI applications. Learn indexing, querying, filtering, and best practices for RAG systems

Local Text Embeddings with Sentence Transformers — Complete Guide

Learn how to generate high-quality text embeddings locally using Sentence Transformers. Complete guide to embedding models, batch processing, and optimization f

Document Chunking Strategies for RAG Systems — Complete Guide

Master document chunking strategies for RAG systems. Learn about semantic chunking, overlapping windows, chunk size optimization, and metadata enrichment for be

Q1 2026 IT Quarterly Review | Infrastructure, Open Source, and AI Operations

Q1 2026 IT Quarterly Review: AI infrastructure becomes a macroeconomic force, the EU AI Act moves from theory to operational deadlines, and…

PDF Data Extraction with PyMuPDF (fitz) — Complete Python Tutorial

Working with PDF documents programmatically is a common challenge in data processing, document management, and machine learning pipelines. Whether you’re building a…

📁 IT Quarterly Review

5th January 2026 22 min