Ollama is a practical platform for running large language models locally on personal computers, workstations, or private servers. It allows users to experiment with open-source models, build local AI workflows, and perform inference without relying entirely on cloud-based services. This is particularly useful for privacy-conscious applications, prototyping, coding assistance, document analysis, retrieval-augmented generation, and educational projects. This tag collects articles on Ollama setup, local model management, prompt testing, integration with Python or other tools, and the broader role of Ollama in building personal and private AI systems.
There is a specific moment, familiar to anyone who has gone down this road, when you finish downloading a model with “Med” in its name and realise you have no idea whether it is actually any good. The name promises domain expertise. The model card promises benchmarks. Neither tells you what happens when you ask … Read more
Part 4: the conclusion of the “Local AI” series — The LM Studio surprise: same model, same hardware, 40-200x faster In Part 3, we pushed gemma4:e4b through four demanding tests. The results were impressive — excellent clinical reasoning, comprehensive summaries, working code. But the wait times were brutal: 5 to 16 minutes per response on … Read more
Part 3 of the “Local AI” series — Coding, reasoning, medical summarization, and clinical decision support Benchmarks tell you how fast a model runs. They don’t tell you if it can actually do anything useful. In Part 1 we set up Ollama, and in Part 2 we measured generation speeds. Now we push these models … Read more
Part 2 of the “Local AI” series — Benchmarks and recommendations for CPU-only inference In Part 1, we installed Ollama and ran our first local model. Now the question becomes: which model should you actually use? The answer depends on your hardware and your patience. On CPU-only systems, model size directly impacts speed — and … Read more
Part 1 of the “Local AI” series — A practical guide to running local LLMs on CPU-only consumer hardware You’ve probably heard that running AI models locally requires expensive hardware: a Mac with Apple Silicon, or a gaming PC with a high-end NVIDIA GPU. This isn’t entirely wrong — those setups are faster. But they’re … Read more