Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

Post by oakesm9 » Fri, Jan 23, 2026, 5:24 PM UTC

ihales wrote: post #150

theophaniel wrote: post #80

Earlier quoted context omitted.

Could you give the gist / config on how you made it work with Zed ?

I had Claude add it as an edit-prediction provider (running locally on llama.cpp on my Macbook Pro). It's been working well so far (including next-edit prediction!), though it could use more testing and tuning. If you want to try it out you can build my branch: https://github.com/ihales/zed/tree/sweep-local-edit-predicti... If you have llama.cpp installed, you can start the model with `llama-server -hf sweepai/sweep-…

Post by kevinlu1248 » Fri, Jan 23, 2026, 6:17 PM UTC

kamranjon wrote: post #4

I read the release but didn't quite understand the difference between a next-edit model and a FIM model - does anyone have a clear explanation of when to use one over the other? I'd love if there was a sublime plugin to utilize this model and try it out, might see if I can figure that out.

Post by ihales » Fri, Jan 23, 2026, 10:31 PM UTC

oakesm9 wrote: post #151

ihales wrote: post #150

Earlier quoted context omitted.

I had Claude add it as an edit-prediction provider (running locally on llama.cpp on my Macbook Pro). It's been working well so far (including next-edit prediction!), though it could use more testing and tuning. If you want to try it out you can build my branch: https://github.com/ihales/zed/tree/sweep-local-edit-predicti... If you have llama.cpp installed, you can start the model with `llama-server -hf sweepai/sweep-…

This is great and similar to what I was thinking of doing at some point. I just wasn't sure if it needed to be specific to Sweep Local or if it could be a generic llama.cpp provider.

Post by jmanandchanny » Sat, Jan 24, 2026, 6:43 AM UTC

evanreichard wrote: post #69

_ache_ wrote: post #14

It's good. The blog post about it is very interesting. I hope, a plugin for neovim will be made soon. https://blog.sweep.dev/posts/oss-next-edit

There's also https://github.com/ggml-org/llama.vim Which I've been using with Qwen3 Coder. As long as infill is supported, that should work. I'll try later today.

Post by keepamovin » Sun, Jan 25, 2026, 9:19 AM UTC

kevinlu1248 wrote: post #156

keepamovin wrote: post #145

Earlier quoted context omitted.

Totally this. But the corp labs have incentives to keep researching per investors and staffing load, so they have to show work. I guess a nice advantage of backwardness here is that economic opportunities exist for those who can solve pain points in the use of existing intel. Older models often do almost as well at agentic tasks in reality, can probably go further. Still, AGI should remove a lot of this making it red…

Ya definitely, that makes total sense. It feels to me that currently the labs have great researchers, who only care about making models perform better across raw intel and then they have incompetent applied AI engineers / FDE's who can only suggest using better prompting to remove bad habits to make agents more usable.