Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I was somewhat surprised to find that Zed still doesn't have a way to add your own local autocomplete AI using something like Ollama. Something like Qwen 2.5 coder at a tiny 1.5b parameters will work just fine for the stuff that I want. It runs fast and works when I'm between internet connections too.

I'd also like to see a company like Zed allow me to buy a license of their autocomplete AI model to run locally rather than renting and running it on their servers.

I'd also pay for something in the 10-15b parameter range that used more limited training data focused almost entirely on programming documentation and books along with professional business writing. Something with the coding knowledge of Qwen Coder combined with the professionalism and predictability of IBM Granite 3. I'd pay quite a lot for such an agent (especially if it got updates every couple of months that worked in new documentation, bugfixes, github threads, etc to keep the answers up-to-date).



You don't have to buy a license; the autocomplete model is open source https://huggingface.co/zed-industries/zeta

It is indeed a fine tuned Qwen2.5-Coder-7B


> I'd also pay for something in the 10-15b parameter range that used more limited training data focused almost entirely on programming documentation and books along with professional business writing.

Unfortunately, pretraining on a lot of data (~everything they can get their hands on) is needed to give current LLMs their "intelligence" (for whatever definition of intelligence). Using less training data doesn't work as well for now. There definitely not enough programming and business writing to train a good model only on that.


If the LLM isn’t getting its data about coding projects from those projects and their surrounding documentation and tutorials, what is it going to train with?

Maybe it also needs some amount of other training data for basic speech patterns, but I’d again show IBM Granite as an example that professional and to-the-point LLMs are possible.


There's an active PR providing inline edit completions via Ollama: https://github.com/zed-industries/zed/pull/33616


You can use a local model! It's in Settings in a Thread and you can select Ollama.


But that doesn't work for inline edit predictions, right?


Ditto, that was one of the dealbreakers for me using Zed, the Copilot integration is miles behind Cursor's


> Ollama

You mean an locally run OpenAI API compatible server?


thats why i created myself nanocoder 0.5b FT for autocomplete in couple of days going to release a v2 version much better

https://huggingface.co/srisree/nano_coder




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: