Sweep Next-Edit 1.5B

AI

code autocomplete model

SHOW HN2026

534points
153comments
#43of 4,366 in 2026
Top 1%of 2026 by points

How HN took it

CuriousMostly questions and neutral comments

23 positive, 69 neutral or asking, 1 mixed, 5 critical, out of 98 comments about the project. Thread score +0.22.

Idea: 8 for, 1 againstPerformance: 5 for, 1 againstExecution: 2 for, 1 againstPrivacy: 1 for, 1 againstDocs: 1 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Strong performance and quality for a small local model.

    From 3 comments
    • Hi, I tried the model and I am super impressed by the performance/quality. Thanks for making this open source! I am the author of this Neovim plugin for edit completions. I was…
      leonardcser on HN
    • 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…
      notsylver on HN
    • Wow, I can even chat about C code with that model with LM Studio on my Macbook at 200 tokens per seconds
      ttoinou on HN
  • Useful open weights that could replace paid autocomplete subscriptions.

    From 2 comments
    • 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…
      vanillameow on HN
    • 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…
      notsylver on HN

Objections

  • Suggestions are overeager and some code quality is poor for C#.

    From 1 comment
    • At least for C#, the quality of the cloud offering is rather mediocre, so I don’t expect this model to be that useful there. It’s very overeager, suggesting tons of stuff that I…
      Semaphor on HN
  • Suggestions are not impressive compared to larger models.

    From 1 comment
    • I've been trying my hands at implementing an emacs package for inline completions with this. I have it mostly working and performance is good enough but I haven't been blown away…
      cmrdporcupine on HN

Requests

  • Support for VSCode and Neovim integration.

    From 3 comments
    • Wow super fun read, I love how it went into the technical details. Any way to make it work with vscode?
      syntaxing on HN
    • Any easy way to try on vscode?
      dainiusse on HN
    • Has somebody built any vscode extensions for this? Also is anyone serving this model?
      dubesar55 on HN
  • Ollama or LM Studio support.

    From 2 comments
    • Hey, ollama run as suggested in hf doesn't seem to work with this model. This worked instead: ollama pull hf.co/sweepai/sweep-next-edit-1.5B
      woile on HN
    • I'm playing around with this in LMStudio (in huggingface -> use this model dropdown -> LMStudio) It's really impressive so far, so quick to respond on a mac mini M2. And it…
      keyle on HN

Questions

  • Is the training data available?

    From 1 comment
    • 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.
      zoobab on HN
  • Does the JetBrains plugin run offline or phone home?

    From 2 comments
    • Very cool! I understand that the 1.5B is small enough to run locally... but does it actually in the Sweep AI Jetbrains plugin? That is, if I install the plugin, will I download…
      kleiba on HN
    • Can this be used offline in Jetbrain IntelliJ? Looking at the plugin, it looks like it requires sign in and then it uses the cloud based model instead of the local one. Can't tell.
      smusamashah on HN

Alternatives named

  • GitHub Copilot

    From 2 comments
    • 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…
      vanillameow on HN
    • Really cool. But how to use it instead of Copilot in VSCode ?
      jedisct1 on HN
  • Continue.dev

    From 1 comment
    • I remember using Qwen 2.5 Coder for autocomplete with Continue.dev, that experience was a mess both in JetBrains IDEs, as well as Visual Studio Code. People posting stuff like…
      KronisLV on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/46713106)