Browsing Tag
ollama
8 posts
Building a Local, Multimodal AI Terminal Agent with Gemma 4
Introduction Open-source LLM models have been improving rapidly with tool calling, extended context windows, and native vision and…
Six queries, three runs, every mean 8 — and the fine-tune wasn’t why
The bar we set We approved a plan on 2026-07-10 with an acceptance test we weren’t sure was…
No API Keys. No Cloud Bills. No Data Leaving My Machine. Here’s Exactly How — and What It Actually Costs
Most people use AI the same way: Open ChatGPT, Claude, or Gemini. Ask a question. Get an answer.…
Giving Your Local LLM Safe Filesystem Access With Ollama Tool Use
A local LLM that can read your files is genuinely useful. A local LLM that can read your…
Hermes Agent Burned 603M Tokens Behind My Back — I Cut Background Costs by Up to 125x
Last Tuesday I noticed my Ollama Cloud Pro quota draining faster than usual. Way faster. I had burned…
The Complete Guide to Local AI Coding in 2026
The Complete Guide to Local AI Coding in 2026 TL;DR: Qwen2.5-Coder-32B scores 92.7% on HumanEval (matching GPT-4o), runs…
Tool call with local model using Ollama and AutoGen.Net
Ollama, starting from version 0.3.0, supports tool calls with popular models like llama 3.1 and mistral. This functionality…
AI/ML – Langchain4j – Chat Memory
In the preceding article, we were introduced to AI/ML concepts and explored the process of running a local…
