Fast AI coding with Qwen 2.5 and Cursor

In this video, I will teach you how you can combine the AI native code editor Cursor with one of the best open-source AI models for coding today: Quen 2.5 30b! Other powerful local models are also supported.

📌 Timestamps:
0:00 - Introduction
1:00 - Powerful models in LM Studio
2:50 - Proxy Configuration
5:00 - Set up custom models in Cursor
7:25 - Qwen 2.5 30b model usage in Cursor

Music track: Creamy by Aylex
Royalty Free Music for Videos (Safe)

🌐 Find me online:

#llm #coding #softwaredeveloper #ai #artificialintelligence

[thedevo]

So I guess the best target demographic for this solution is someone who's a subscribed user of Cursor, who wants a second model to fill in the blind spots and has enough memory to run a model locally.

the most comprehensive video on the subject !!!! thank you so much for this.. my question is. would it be possible to work in composer mode of cursor too?

[phoenyfeifei]

3:02 ok, that makes sense, i was wondering why you revert forward your ports since you can alerady run a serve locally

[mnageh-bomm]

Hmm first time to hear about the LLM studio, also nice solution for the ngrok

[thegtlab]

How does it compare to 4o and sonne t for actual practical use? I’m tired of reviewers just doing simple html games I want real actual tasks.

[HimanshuChanda]

Quick question in case, if cursor provides unlimited usage, why would somebody want to switch from Claude to Qwen ? Are there any restrictions or is QWEN much better?

[hannespi]

Great video. Looking forward to use it once cursor allows for composer to take this

[SavunCheam]

Well done. But I am still wondering if there is a way to change model for completions too (code suggestion on typing). Thanks

[anaskhan-lzhk]

I appreciate your video but using cursor with local model is not better way not only it need ngrok setup but also the composer will not work there are better alternatives like aider and continue dev.

[ConservativeWatchParty]

This video is hard to follow. I feel it would be easier if you cleared your screen and had less going on so that the viewers Eyes knew where to go. Showing unnecessary code all over your screen makes it very confusing for beginners to identify what they are supposed to be looking at. Also you may consider being more clear about which tabs you are pressingand navigating through your screen. I appreciate the video and I look forward to a less confusing one.

[XCLIPS_VIDEO]

If I deploy the model locally, do I need to pay a cursor subscription in the future. Or since it is my model, I can use it as much as I want?

[abanoubashraf]

which plan re you on cursor? the free one?

[AINMEisONE]

How can you get the same coding ability as CLINE with Sonnet, Openai and Gemeni where they modify inline the code and changes are shown live. Is there a way?

[b.c.]

I installed for test and it replies with strange code. Looks like encrypted information :(

[blankslate]

Nice and conscise guide but sadly this clever trick does not work anymore. Now curser wants to verify the 'OpenAI' key, which results in Invalid OpenAI API Key`. Bastards! We need an alternative open source cursor otherwise they ai gang will squeeze the last bits of money out of us.

[yokuna-bm]

Hi guys! Thank you for your great video.
And have a question, my macbook pro m1 (RAM : 16GB), download Qwen 2.5 32b, but can't load this model in LM studio. please hep me.
I wan know your pc or laptap spec.

[ruslanmakarov]

Only for Cursor Chat, does not work for Supercomplete or Composer
Pretty much useless

[nesdi]

Qwen is a model from Alibaba and Alibaba has sanctions against it, I'll be not using Qwen thanks. Also something about cursor that rubs me the wrong way seems to be too much hype and that it's being shoved down our throats