Comparison: Qwen3:30b vs GPT-OSS:20b
Comparing Speed, parameters and performance of these two models
Here is a comparison between Qwen3:30b and GPT-OSS:20b focusing on instruction following and performance parameters, specs and speed:
        
    Comparing Speed, parameters and performance of these two models
Here is a comparison between Qwen3:30b and GPT-OSS:20b focusing on instruction following and performance parameters, specs and speed:
        
    Approximate hosting cost estimations vs subscription.
Here’s a quick info on Write.as / WriteFreely - how it fits into the fediverse, where to get managed hosting, what the usage trend looks like, and how to self-host (plus rough costings).
        
    + Specific Examples Using Thinking LLMs
In this post, we’ll explore two ways to connect your Python application to Ollama: 1. Via HTTP REST API; 2. Via the official Ollama Python library.
        
    What is Proxmox?
Proxmox Virtual Environment (Proxmox VE) is an open-source, type-1 hypervisor and datacenter orchestration platform built on Debian.
        
    What to do with `canonical`, `lang` and `hreflang`
Translating your Hugo website can improve your Google and Bing ranking - but only if the translated content is high quality, localized, and properly structured for multilingual SEO.
        
    Including intallation instructions for Windows, Linux and Mac
Online privacy is a hot topic. From targeted ads to silent trackers, many mainstream browsers share more about you than you’d like. Fortunately, several privacy-oriented browsers exist to help you stay safe and anonymous.
        
    AI-suitable Consumer GPU Prices - RTX 5080 and RTX 5090
Let’s compare prices for top-level consumer GPUs, that are suitable for LLMs in particular and AI in general. Specifically I’m looking at RTX-5080 and RTX-5090 prices. They have slightly dropped.
        
    How to develop Amazon Alexa Skill - instructions.
In this article, we’ll take a deep dive into Alexa skill development, testing, and publishing. We’ll also cover design principles, technical considerations, and best practices to ensure your skill provides an engaging and natural user experience.
        
    Not very nice.
Ollama’s GPT-OSS models have recurring issues handling structured output, especially when used with frameworks like LangChain, OpenAI SDK, vllm, and others.
        
    Slightly different APIs require special approach.
Here’s a side-by-side support comparison of structured output (getting reliable JSON back) across popular LLM providers, plus minimal Python examples
        
    A couple of ways to get structured output from Ollama
Large Language Models (LLMs) are powerful, but in production we rarely want free-form paragraphs. Instead, we want predictable data: attributes, facts, or structured objects you can feed into an app. That’s LLM Structured Output.
        
    Quick reference to postgresql
A quick reference for day‑to‑day PostgreSQL work: connections, SQL syntax, psql meta-commands, performance, JSON, window functions, and more.
        
    Using pandoc, python, or online tools for convertion to MD
Converting Word documents to Markdown format is a very common task for technical writers, developers, and content creators who want to move their content to platforms with Markdown (like GitHub, GitLab, static site generators like Hugo).
        
    A practical, code-heavy look on ORMs in GO
Most prominent ORMs for GO are GORM, Ent, Bun and sqlc. Here is a little comparison of them with examples of CRUD operations in pure GO.
        
    A bit of Jabber / XMPP statistics
Jabber (now commonly referred to as XMPP) is an open-source communication protocol and suite of client applications that enable instant messaging, voice/video calls, conferencing, desktop sharing, and presence features for individuals and organizations.