English
Deutsch
Polski
Laptop, Mini PC, GPU Tower or AI Workstation: Which Devices Suit Local LLMs?
Compare CPU devices, Apple, AMD APUs, GPU towers and DGX Spark by memory, software, upgrades and workload.
Cloud & AI
20 articles in this category
Follow this category by RSSAbout this category
A cloud service, a container of your own or a local AI model: there is often more than one way to get something done. Here I look at how these options work, what they cost and what it takes to run them.
Topics include containers, serverless, AI APIs, local language models, RAG and automation. I explain the building blocks and their limits to help you assess an idea and plan your next steps.
Q4, Q8, FP16 and Long Context: Why a Local LLM Can Fail Despite Fitting on Disk
Plan weights, cache and runtime headroom together: Q4, Q8, FP16, long context and hybrid architectures compared.
Freely Available LLMs Compared: Qwen, Gemma, Ministral, Llama and DeepSeek for DE, EN and PL
Compare Qwen, Gemma, Ministral, Llama and DeepSeek by language, task, memory and licence, using separate DE, EN and PL evaluations.
Ollama, LM Studio, llama.cpp or vLLM: Which Software Fits Local LLMs?
A task-based comparison covering desktop chat, local APIs, Apple optimisation and server workloads.
Web Bot Auth: How Agent Requests Are Signed and What the Signature Proves
Web Bot Auth signs agent requests with Ed25519 per RFC 9421, publishes the public key as a JSON web key set at a fixed well-known path, and lets a site verify who asked. It proves the operator and the domain – and nothing at all about intent.
Compare AI Model Costs: Cloud APIs or Local DeepSeek and Qwen?
Current API rates, local operating costs and cost per accepted task for GPT, Claude, Gemini, DeepSeek and Qwen.
Which AI Models Fit German, English and Polish?
Compare GPT, Claude, Gemini, DeepSeek and Qwen by terminology, meaning and language quality in DE, EN and PL.
AI Models for Research and Documents: Gemini, GPT and Claude versus Open LLMs
Compare Gemini, GPT, Claude, DeepSeek and Qwen through document processing, source evidence and local search.
Automated Enterprise Reporting: PDF Generation with Python & OpenAI API
A technical step-by-step tutorial on building an automated PDF reporting pipeline using Python, Pandas, and the OpenAI API for AI-generated summaries.
AI Models for Coding: GPT and Claude versus DeepSeek and Qwen
Compare current coding candidates through code quality, repository work and local deployment.
