0
Prompts
Alibaba Runs locally
Qwen
Qwen comes in sizes that fit almost anything, from a model small enough for a phone to one that wants a full workstation. Its multilingual training makes it a sensible default for non-English work. The smaller sizes follow one short, direct instruction better than a long one with several conditions stacked on it.
0
Configs
Modelfile
Config file
Yes
Runs locally
Nothing published for Qwen yet.
If you have a prompt or a config that works here, it would be the first.
Share oneCommon questions
Where do you put standing rules for Qwen?
In Modelfile. It is read on every session, so anything you would otherwise paste into each message belongs there rather than in the conversation.
Do Qwen prompts work on other models?
Usually with changes. Every resource here records where it was tested and what to adjust elsewhere, and portable ones are filed under Universal.
Can Qwen run on my own machine?
Yes. Memory is the constraint: a 4-bit quantised model needs roughly 0.6 GB per billion parameters plus room for the context window.