Ollama vs MS Foundry Local: Benchmarking Local LLMs on an RTX 5070
Following up on Foundry Local in VS Code, I wanted hard numbers. I built Ollama BenchRig to benchmark llama.cpp against ONNX Runtime GenAI on real developer workloads.
Senior Solution & Enterprise Architect • AI & Industrial IoT
Hi, I'm Rafał Warzycha
Enterprise & Solution Architect with 18+ years of experience (since 2008) across industrial IoT, cloud data platforms, and AI governance. Here I share deep dives, guides, and thoughts on AI/LLM engineering, IIoT architectures, cloud infrastructure, and software craftsmanship.
Recent Articles
Latest posts and tutorials
Foundry Local Chat — bringing local models into VS Code's chat picker
I run Foundry Local for the obvious reasons: no cloud round-trip, no API key, no per-token bill. What I didn't have was a way to use those downloaded models fro
Sample C/C++ consumer and producer implementation for Azure EventHub with Kafka surface
Since there I wasn't able to find any existing libraries for connecting to Azure EventHub from C/C++ using native EventHub Kafka surface capabilities and using librdkafka to achieve it.
ESP32 and cloud IoT - "Hello world" in ESP32 IDF
In this tutorial, I will walk you through all steps required to build, flash, and monitor your own firmware.
ESP32 and cloud IoT - Setup and pre-work
As I promised in my workshop during "Lodzkie Dni Informatyki," this is the first entry that will be all about setup and pre-work.nThis short post will walk you through all the required hardware and software to start your journey with ESP32 and cloud IoT.
Homebrew weather station
Today I would like to share with you some small IoT project that I did a few weeks ago. It was a homebrew weather station. Here are in details instruction how I