Mistral-Nemo + Stable-Code + Twinny : THE BEST Local Coding Copilot is here! (BEATS Github Copilot)

[@ManuelJimenez1]

Ouch! You have done it! Great! Amazing dude! THANKS!

[@badanimz1453]

I found myself watching all of your videos lol but one thing you never explain is how many resources we need to run the local llm

[@remi8118]

Wow it's seam instantaneous ! on what machine did you run the model ? I tried to use mistral nemo on a 4090 (using python) but the message get 5 min before being return by the model.

[@ThanhXuan-ix4fl]

Great instruction! Btw, can you make a video about fine tune?

[@Chatec]

Are you creating a video for aider using this?

[@computingsafety]

Intro is the best 😁 welcome to another happy day with AI

[@programmersemarang]

Finally it's here

[@hollidaycursive]

Dancing to the intro

[@mdubbau]

Love it thanks @AICodeKing!

[@mdubbau]

This is the first-time I've made a Super-Thanks contribution to any channel. Thank you kindly!

[@vauths8204]

This plus aider would be a huge advancement

[@uselesdev]

How are you doing this? Its literally more than 1 high quality videos per day.

[@yngeneer]

what about deepseek coder v2 ? isn't it better for coding than nemo? btw doesn't ds coder v2 get some update recently?

[@crushfire2004]

This channel already has review on new deepseek-coder-v2 recently. Just check it out.

[@papillon8i838]

Couldn't get completion to work. Out of the box it uses markdown with a bunch of explanatory text. I changed the prompt, turned off multiline completion in config. Still markup and unusable. Changed to stable-code and completion stopped working completely. Deleted and reinstalled extention. It remembered model making me think it didn't really uninstall. Would be nice if I could get it to work. Thanks for vid. shell-gpt was new to me. Cheers.

[@remedyreport]

Thank you

[@vauths8204]

Have you tried Agent Zero yet?

[@aryindra2931]

Wow new intro 🎉🎉

[@papillon8i838]

VScode refuses to actually uninstall it, keeps coming back with edited prompt. Now I have to find out how to manually kill the thing.

[@ThangNguyen-ot8uz]

So in the company's perspective, do I have to provide each of my employee a GPU to run this?

[@AICodeKing]

No, You can get an API from Mistral or Nvidia and connect that with ContinueDev.

[@ThangNguyen-ot8uz]

@@AICodeKing is there anybody doing a video about what's the cost comparision of these 3 options: (1) use smt like copilot and pay 20-29$ per person ; (2) use some API from mistral & nvdia like you said ; (3) invest on hardware to run locally ? I think for option 3 to be viable for companies, we will have to refine the hardware spec very carefully to get the most value out of it.

[@mdubbau]

Thanks!

[@AICodeKing]

Thanks a lot ❤️

[@gani2an1]

Still waiting for aider deepseek coder for editing local files

[@internetmarketingproductre6093]

It already works , aider and deepseeker , you need add the local file with command

[@Mr-hn4bo]

How to make it work with ollama running on docker?

[@AICodeKing]

You can do that by changing the base url

[@prometheas]

“Anyway”

[@CodeWithAbirOfficial]

On windows, i am using LM Studio. can any want tell me how to integrate this with vs code.?

[@AICodeKing]

Yes, you can do that with ContinueDev