QuickerSite Blog

A self-contained, single-file HTML application that runs Classic ASP/VBScript code entirely in the browser, powered by ASPPY and Pyodide (Python compiled to WebAssembly). No server required  just open it in any modern browser.

Just to clarify things: your ASP code never leaves the browser. There is NO server involved! Your browsers WebAssembly acts as the server for your ASP scripts.

https://pietercooreman.github.io/ASP-Runner/

Github repo: https://github.com/PieterCooreman/ASP-Runner

Today was supposed to be the day. My long-awaited AI Lab hardware finally arrived, and I was ready to dive right into setting up my ultimate local environment. But plot twist: they shipped the 64GB RAM edition instead of the 128GB beast I actually ordered.

So, I’m temporarily grounded. At least, as far as my grand vision of running a powerhouse local AI lab is concerned. But after the initial frustration wore off, I had a realization. Maybe I don't actually need my own massive local AI setup. In fact, I might not need it at all.

Here is why: the landscape of cloud-based AI is shifting incredibly fast, and Chinese LLMs are steadily taking over the scene. The cloud versions of Deepseek, Qwen, and above all, Mimo are absolutely amazing. The best part? If they aren't entirely free, they are stunningly cheap. We are talking a fraction of the cost of heavyweights like Claude, Gemini, or GPT, while delivering near-parity performance.

Right now, these Chinese models are estimated to be only about seven months behind the top-tier US-based AI giants. When you factor in the massive cost savings and the sheer speed of development, building an expensive local rig suddenly feels a lot less urgent.

So, in all honesty, maybe getting the wrong hardware was exactly what I needed to step back and look at the bigger picture. All I really have to do right now is save my money, tap into the cloud, and just be a little patient.

If you own a Classic ASP/VBScript application, you've probably felt the deadline pressure: Microsoft is phasing VBScript out of Windows, and the usual advice is to rewrite everything. There's a better option.

ASPPY is an open-source runtime, written entirely in Python, that executes your existing .asp pages on Windows, Linux, and macOS — no IIS, no COM, no rewrite. Your familiar Request, Response, Server, Session, and Application objects just work, and a new ASPPY global object adds modern superpowers (JSON, PDF, image processing, ZIP, bcrypt, and mail) straight from VBScript.

I've put together a free, practical guide that walks you through all of it — the philosophy, the setup, the legacy object model, and a deep-dive into every extension, with side-by-side "legacy way vs. ASPPY way" examples. Every code sample in the book was actually run against ASPPY before it made the page.

Read it here: https://pietercooreman.github.io/ASPPY/ASPPY_The_Vibe_Coders_Guide.html

Yesterday, I built this: https://qwencrm.quickersite.com/ on ASPPY using Qwen 3.6 Plus using OpenCode.ai. It's hosted in IIS, but on the ASPPY web server, solely relying on Python. Zero ASP/VBScript dependencies. Yet 100% pure Classic ASP/VBScript.

Cost? 1.64 USD. That's less than 1.5 EUR.

Specs:

• Multi-user CRM
• 100% responsive/user-friendly Bootstrap 5.3 front-end
• Unlimited contacts/companies/leads
• Dashboard
• Sorting/Filtering/Searching
• Activity log

All that for less than 2 EUR of vibe coding with Qwen 3.6 Plus. I already regret having bought my own hardware. Qwen 3.6 Plus is believed to support over 1 million token contexts. And it's good. Very good even. To give an idea: this CRM took 136.600 tokens 

I used the ASPPY prompt builder to get this started, on a fresh install of the GitHub ASPPY codebase. I used a minimal prompt: "SaaS solution that acts as a CRM with contacts, companies, leads and activity log." That's it. I pasted that in the prompt builder. The prompt builder turned this into a superprompt, and Qwen did the rest. A handful of corrections and fixes later, it was done. Below 2 EUR. Still can't believe this.

There is an open-source (100% free!) variant of Qwen 3.6 (Qwen 3.6 27B) that I will be able to test next Wednesday. This might be a game changer for developers, as it will allow us to locally install a free coding agent that spits out world-class web applications in no time, on affordable consumer hardware (starting at 4000 EUR).

By the time I click the save button below, this post is outdated. Things are rapidly changing in 2026.

I did a bit of research.

Below you can find 13 SVG files that were all generated with one and the same prompt by 13 different AI LLMs:

I used 3 local LLMs: Gemma 4 e4b, Qwen 2.5 Coder 7b and Qwen 3.5 9b. Let's be honest. They are useless.

But... take a look at the Qwen 3.6 Plus variant. This is a proprietary model hosted by Alibaba, the well known Chinese web shop.

However, Qwen 3.6 27B was recently (April 2026) released as an open source and free model that can be installed locally, on powerful consumer hardware. It appears to be a gamechanger for local agentic coding. I can't wait to give this LLM a try.

Meantime I developed my own AI chatbot on https://github.com/PieterCooreman/Synapse. Synapse connects to locally installed LLMs (via Ollama or LM Studio) and tries to get the best results possible. 

I'll be back with more news about Qwen 3.6 27B. I have high expectations. I recently bought a 128GB RAM desktop horse. It should run this LLM at a reasonable speed.

 Meantime, check out this document, generated by my locally installed Gemma 4 b31 (model by Google). Gemma 4 is pretty good at authoring texts. But it's not very good at coding. Qwen is much better with code. Both models can be installed simultaneously on Ollama or LM Studio, giving you more flexibility when deploying a local AI Lab.