Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete • Hacker News Board

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

#61

Post by notsylver » Thu, Jan 22, 2026, 11:09 AM UTC

I've been waiting for something like this for ages. Cursor making me pay $20/month when all I use from it is autocomplete was always a little annoying, especially as they changed the UI to push agents more and it got in the way. I was even considering doing it myself but wasn't sure about gambling on models small enough to run locally being smart enough to do anything useful.

I threw together a vscode extension to run it and while the extension is rough, the model seems decent. I'm trying to keep my expectations contained, in the past local models have been absolutely terrible for inline completion, this seems much better already. I hope this kicks off more competition.

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

#62

Post by zoobab » Thu, Jan 22, 2026, 11:18 AM UTC

Where is the training data?

We can't keep calling those models "open source" if we have a black box and know precisely how they were made.

"Open weights" are the new binary.

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

#63

Post by replete » Thu, Jan 22, 2026, 11:29 AM UTC

jedisct1 wrote: post #40

Really cool. But how to use it instead of Copilot in VSCode ?

Run server with ollama, use Continue extension configured for ollama

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

#64

Post by mromanuk » Thu, Jan 22, 2026, 11:51 AM UTC

_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 is one already, on of the plugin authors commented here

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

#65

Post by cmrdporcupine » Thu, Jan 22, 2026, 11:55 AM UTC

vanillameow wrote: post #39

Sometimes when I use a plugin like this I get reminded just how much of a productivity nerf it is to code without an autocomplete AI. Honestly in my opinion if you write a lot of boilerplate code this is almost more useful than something like Claude Code, because it turbocharges your own train of thought rather than making you review someone else's, which may not align with your vision. This is a really good plugin.…

Yep. I'm coming to resent Claude Code and tools like it for taking me out of direct contact with the code.

I think we're still in the early days of these systems. The models could be capable of a lot more than this "chat log" methodology.

Agree about JetBrains dropping the ball. Saddens me because I've also been a diehard user of their products since 2004.

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

#66

Post by BoredomIsFun » Thu, Jan 22, 2026, 12:12 PM UTC

jychang wrote: post #35

vichle wrote: post #34

What type of hardware do I need to run a small model like this? I don't do Apple.

1.54GB model? You can run this on a raspberry pi.

Performance of LLM inference consists of two independent metrics - prompt processing (compute intensive) and token generation (bandwidth intensive). For autocomplete with 1.5B you can get away with abysmal 10 t/s token generation performance, but you'd want as fast as possible prompt processing, pi in incapable of.

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

#67

Post by BoredomIsFun » Thu, Jan 22, 2026, 12:13 PM UTC

replete wrote: post #63

jedisct1 wrote: post #40

Really cool. But how to use it instead of Copilot in VSCode ?

Run server with ollama, use Continue extension configured for ollama

I'd stay away from ollana, just use llama.cpp; it is more up date, better performing and more flexible.

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

#68

Post by lelanthran » Thu, Jan 22, 2026, 12:18 PM UTC

oefrha wrote: post #28

plutodev wrote: post #2

[flagged]

You’re subtly pushing the same product in basically every one of your comments. If these are good faith comments please edit out the product name, it’s unnecessary and doing so as a green account just makes people consider you a spammer. Establish yourself first.

Or he could disclose it.l, which he did in a different comment on a different story.

I agree that green accounts could be regarded as suspicious and, if it were me, I'd disclose each time I mention it.

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

#69

Post by evanreichard » Thu, Jan 22, 2026, 12:35 PM UTC

_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.

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

#70

Post by mgz » Thu, Jan 22, 2026, 1:07 PM UTC

8n4vidtmkvmk wrote: post #19

mgz wrote: post #5

I use Sweep’s Jetbrains autocomplete plugin daily, it really stands out.

Better than the one that ships with Jetbrains? I did buy their $100/yr AI but its about to run out.

Definitely better. Next edit makes a difference. But it is not free, I think I pay $10/month.