>You can't vibe code without using a service from a big company, and obeying their rules.

In abstract, probably true, but so vague to be useless.

I can probably vibe code with qwen on debian. But are you then going to pivot from your microsoft example to like, my ISP? And if I point out I can move to an ISP with less than 5 staff, you will probably just move the goalposts further right?

Might be better to let you establish your goalposts first hey.

▲

kragen 15 hours ago | parent [-]

What has your experience vibecoding with Qwen on Debian been like so far? What tooling and approaches have you found to work best?

▲

protocolture 10 hours ago | parent | next [-]

I use it on Windows, I am just loosely aware that I could run it on debian if I wished. I use 7b and its roughly as useful as GPT 3.5. I dont have any tools linked to it yet.

	▲	kragen 10 hours ago \| parent [-]
		Does that mean "pretty useful" or "a total waste of time"? I never got much useful code out of GPT 3.5.

▲

brazukadev 14 hours ago | parent | prev [-]

I'm implementing an MCP client using Qwen3 4B and its tool call capabilities are impressive! I'm sure it will only improve and the 30B is probably already much better.

▲

kragen 14 hours ago | parent [-]

What are you running it in, ollama? Did you have to install some additional software to enable it to call tools (also via MCP?)

	▲	brazukadev 4 hours ago \| parent [-]
		LM Studio. No additional software but I implemented the MCP client myself using the typescript-sdk[0] 0. https://github.com/modelcontextprotocol/typescript-sdk