AI
Running Qwen3.8 Flash-Next on Dual RTX 3060s with Proxmox and llama.cpp
An experimental case study of running Qwen3.8 Flash-Next on dual RTX 3060 GPUs and dual-socket Xeon …
Building a Local AI Coding Workstation with Qwen3.8-27B and llama.cpp
An empirical case study of a dual-GPU Linux workstation for local coding assistance with …
LiteLLM: Your Self-Hosted AI Gateway for Local and Cloud Models
Unify Azure AI Foundry, Ollama, LM Studio, and 100+ AI providers behind a single API with LiteLLM. …
Building RAG Pipelines with Kernel Memory
Stop hallucinations and ground your AI in your own data. Build a 'Troubleshooting Bot' using …
Running Local AI with .NET and Ollama
Cut cloud costs and improve privacy by running LLMs locally with Ollama and .NET. Learn how to build …
Mastering Semantic Kernel Plugins
Give your AI agents real-world powers by building custom Semantic Kernel Plugins for system …
Hybrid AI: Combining Local and Cloud Models in .NET
Explore a hybrid AI architecture in .NET that uses local ONNX models for speed and privacy, while …
Deploying .NET AI Applications with Docker
A step-by-step guide to containerizing a .NET application with an embedded ONNX model for …
Semantic Kernel vs. LangChain: A .NET Developer's Guide
An in-depth comparison of Microsoft's Semantic Kernel and the popular LangChain framework, tailored …
Building a RAG System with ONNX Runtime and C#
Learn how to build a Retrieval-Augmented Generation (RAG) pipeline in C# using the ONNX Runtime for …