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

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 able to integrate it with the Sweep Edit model.

For anyone who is interested: https://github.com/leonardcser/cursortab.nvim

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 this is really cool because otherwise it kinda feels like nobody gives a crap, for example even with Cline/RooCode/KiloCode there’s no good way for me to hook up an autocomplete model that either runs in Ollama or maybe a remote Cerebras Code model, like KiloCode doesn’t have a proper model configuration option even if it has it for the chat or regular agentic stuff - I don’t get why autocomplete is such a special case.

I guess what I’m saying is that I’m glad someone’s at least trying so I don’t have to keep a Copilot subscription just because I genuinely like their autocomplete and the rest of it is basically wasted: Claude Code and Codex and others are better for the actual chat/agentic stuff, KiloCode and others are really nice IDE plugins.

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. I'm a diehard JetBrains user, I tried switching to VSCode and its various forks many times because of AI but muscle memory from years of use is hard to override. And for a lot of languages JetBrains is just much better, especially out of the box. But they dropped the ball so hard on AI it's unbelievable. Claude Code pulled it back a bit because at least now the cutting edge tools aren't just VSCode plugins, but I was still missing a solid autocomplete tool. Glad this is here to fill that niche. Very likely will be switching my GitHub copilot subscription to this.

I also really appreciate publishing open weights and allowing a privacy mode for anonymous trial users, even if it's opt-in. Usually these things seem to be reserved for paying tiers these days...

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.

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 the model automatically and the plugin doesn't phone home?

Surprising how badly Jetbrains implemented AI. Apparently to such an extent that even after multiple years of LLM's someone felt confident enough to build a company that can do better.

This looks really neat, interesting technical writeup as well!

This is cool! I am more interested in how you guys generated next edit training data from repos, seems like there are lots of caveats here. Would love your insights

Again amazing work! waiting for what you guys cook next

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

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.

Congratulations on training a relatively small model that can beat larger models for this important task.

>We ran a genetic algorithm over 30+ diff formats

Can you you give more information about your genetic algorithm? Did you do crossover over the trained models (for example, ranking by fitness, take 20% most elite and create children by mixing their weights randomly)? Did you have a 'population size' (number of instances) for the genetic algorithms, and if so what was it?

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.

Between GLM-4.7-Flash and this announcement, THIS is what I'm excited to see in this space: pushing the capabilities of _small_ models further and further. It really feels like we're breaking into a space where models that can run on hardware that I actually own is getting better and better, and that has me excited.

Is there a way to use this (or similar) model in Visual Studio? Extensions on Visual Studio Marketplace are clunky and sluggish at best, if they even work at all.

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

  "features": {
    "edit_prediction_provider": { "experimental": "sweep-local" },
  },
  "edit_predictions": {
    "sweep_local": {
      "api_url": "http://localhost:11434/v1/completions",
    },
  }

    "agent": {

        "inline_assistant_model": {

            "model": "hf.co/sweepai/sweep-next-edit-1.5B:latest",

            "provider": "ollama",

        },

    }

}

  "ui_font_size": 16,
  "buffer_font_size": 15,

  "theme": {
    "mode": "system",
    "light": "One Light",
    "dark": "One Dark"
  },

  // --- OLLAMA / SWEEP CONFIG ---
  "openai": {
    "api_url": "http://localhost:11434/v1",
    "low_latency_mode": true
  },

  //  TAB AUTOCOMPLETE (THIS IS THE IMPORTANT PART)
  "inline_completion": {
    "default_provider": {
      "name": "openai",
      "model": "hf.co/sweepai/sweep-next-edit-1.5B"
    }
  },

  //  CHAT SIDEBAR
  "chat_panel": {
    "default_provider": {
      "name": "openai",
      "model": "hf.co/sweepai/sweep-next-edit-1.5B"
    }
  }
}

It sounds like you might be killing Zed's ability to monetize, am I misunderstanding that?

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.

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

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 appears to be accurate at least for the obvious questions.

I couldn't get it to work as an autocomplete of Zed unfortunately. It looks like it's hardwired to work with some providers and LMStudio is not included in the prediction engines list. Has anyone got a work around?

Wow super fun read, I love how it went into the technical details. Any way to make it work with vscode?

So SFT cost less only low hundreds of dollars? (1-10$ per hour per H100 if I'm seeing this correctly).

What about SFT?

Presumably basing this of Qwen is the reason it can be done for so cheap?

How easy is it to re-train these to specific subset of programming languages? Could there be a "ruby+rails+html" version, etc?

This is actually a game changer. I’ve been meaning to want to run models to accomplish exactly this, but don’t have enough VRAM on my GPU for the conventional LLM-method for the most part. This seems to be a far more efficient method of accomplishing a more scoped problem. Thank you for making it open source!

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 never accepted because it made no sense. It’s also producing bad code, wanting me to use `.Result` for async calls instead of simply await-ing.

This is so cool. What is the second order effect of model training becoming democratized? And local models becoming the norm? Tasks like agentic work are well handled by current AI as long as you know what you're doing and can stress the agent against tests/spec, etc.

I am thinking that one effect is:

- it will become normal for meta-models to train a model specific to a particular task/product.

Also, differently, I'm quite sure that AGI is not available on this current path (useful tho it is), but that some algo improvements might crack ubiquitous trainable AGI. Probably including some kind of embodiment to provide world-models and emotions (which are essential to embodied survival and success).

I dont want to hand edit i want the output of better ai model with edit instructions like //update here <code> // new code <code> insert here etc. and local model read the files and apply the updates. I tried generating patch format but both bigger models fail to generate it accurately and smaller models have hard time in using them. Is there some way to do this with this kind of model? or its for completions while editing only?

Any easy way to try on vscode?

Is there an oss model for next word / edits predictions for texts in general? e.g. Typing emails?

I'm very green to this so forgive if this question sounds silly:

Would instead of the RL step a constrained decoding say via something like xgrammar fix syntax generation issue ?

This is really awesome detail. I’m very impressed by the amount of care taken to identify a good template. I started a small hook to try and do this using DSPy prompt optimizers, but haven’t had a compelling use case to try it with.

This seems like an ideal case for trying DFT as well. I’m not sure if you’re using trl, but I’d suggest checking that out.

Wow, I can even chat about C code with that model with LM Studio on my Macbook at 200 tokens per seconds

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

Very interesting - and cool to read about the development process. I'd love to hear more about how genetic algorithm worked here.

I wonder whether we are perhaps the point of usefulness of 'next edit' code development in 2026 though.

Followed your work since the beginning and used it for inspiration for some cool demos on self-healing web scrapers. fascinating to see the transition from original concept to producing models. cool stuff.

Really cool.

But how to use it instead of Copilot in VSCode ?

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 by the quality of its suggestions unfortunately. Which I guess is expected from a 1.5B model.

I'd love to see them making a larger model in the 10-20b range maybe? I know most people wouldn't be able to run that on their machines, but some could.

Running on ollama locally on NVIDIA Spark GB10. Tried it also with vLLM. Pretty fast.

This seems great for code, but can this be used for non-code use cases?

Does anyone know if the 7B model is also available somewhere?

what do people use for Neovim to integrate these models for tab-completion level of stuff. (i.e. non agentic/vibe coding)

Do you plan to release Sweep 3B/7B on HF?

Great! I have been trying to do something similar for Clojure.

This is a great resource to explore similar approach. https://blog.sweep.dev/posts/oss-next-edit

My notes so far https://kapilreddy.me/notes/2024/11/17/building-clojure-slm-...

is there any llm lsp it can integrate well with?

can it be integrated in monaco editor ?

[dead]

[dead]

[flagged]

Based on qwen2.5-coder? seems like a "why not/resume embellish/show VC" type release I guess