Creation of a GitHub bot that uses a local large language model (LLM) via Ollama to automatically review pull requests. When a PR is opened, the bot receives a webhook, retrieves the code diff using G…
Creation of "Local Gemma 4 Content Radar," a privacy-focused editorial tool that runs the Gemma 4 AI model locally to analyze content signals and produce structured publishing decisions. The tool proc…
Memonia, a new AI memory workspace designed to solve the problem of lost project context between AI tool sessions. It features persistent project memory, task tracking, session reports, and automatic …
This article compares three dominant tools for local LLM inference in 2026: Ollama, llama.cpp, and vLLM. Ollama is recommended for personal, non-technical use due to its ease of setup, while llama.cpp…
While llama.cpp's router mode allows loading and unloading individual models via HTTP API calls to `/models/unload`, there is no built-in "unload all" endpoint. The recommended approach for unloading …
Running local AI for software development is not a cost-free solution, as it simply shifts the expense from cloud subscriptions to expensive hardware upgrades, requiring at least 32GB to 64GB of RAM f…
Forge is a reliability layer for self-hosted LLM tool-calling that uses guardrails and context management to dramatically improve performance on multi-step agentic tasks, boosting an 8B model from 53%…
Tool-using research agent built for the Gemma 4 DEV Challenge, which runs locally on the Gemma 4 e2b model via Ollama using roughly 200 lines of Node.js code. The agent accepts a question, selects bet…
The author successfully ran Google's new Gemma 4 open models (2B and 4B parameters) on a laptop using Ollama during Google I/O 2026 week. To make the small 2B model function as a useful research agent…
Fully local AI system using Llama 3 and LangChain to enable natural language querying of an internal SQLite database, eliminating any data being sent to third-party servers and avoiding legal complian…
Detailed, step-by-step guide for building llama.cpp from source on a Dell Precision T5820 workstation equipped with an RTX 3090 Ti, achieving 42 tok/s with Qwen3.6-27B. The author emphasizes that the …
The GGUF file format consolidates all necessary model components—including weights, chat templates, and special tokens—into a single file, offering a more ergonomic alternative to the scattered JSON f…
Ollama, an AI model server, ran on a MacBook with no NVIDIA GPU by using GTAP software to intercept CUDA calls and forward them to a remote DGX Spark workstation with a 128 GB Blackwell GPU. The setup…
The article describes the author's successful setup for running local AI models on an M4 Mac with 24GB of memory, specifically highlighting Qwen 3.5-9B (Q4 quantized) as the best performing model at ~…
Based on the article, the author, a self-described "AI skeptic," successfully used local LLMs (GPT-OSS 20B and Qwen3 Coder 30B) to migrate blog comments, completing the task in a few evenings. The aut…
The author, a software developer, finds generative AI tools like Claude highly useful for certain tasks, such as Java Spring Boot development, but notes that local models are only adequate and that th…