Sweep, Open-weights 1.5B model for next-edit autocomplete
Hey HN, we trained and open-sourced a 1.5B model that predicts your next edits, similar to Cursor. You can download the weights here (https://huggingface.co/sweepai/sweep-next-edit-1.5b) or try it in our JetBrains plugin (https://plugins.jetbrains.com/plugin/26860-sweep-ai-autocomp...). Next-edit autocomplete differs from standard autocomplete by using your recent edits as context when predicting completions. The model is small enough to run locally while outperforming models 4x its size on both speed and accuracy. We tested against Mercury…
Sweep, Open-weights 1.5B model for next-edit autocomplete launched on January 21, 2026 with 534 votes, #16 of 14,585 launches that month and more than 99% of that year's launches.
In plain words
Sweep is an open-source 1.5B language model designed for next-edit autocomplete in code editors. It predicts a developer's next edits by analyzing recent code changes as context, rather than using standard autocomplete. The model runs locally and delivers speed and accuracy comparable to models four times its size. It is available as downloadable weights or through a JetBrains plugin, making it suitable for developers seeking efficient, on-device code completion assistance.
written from the facts on this page · September 2026
From the sources
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A 1.5B parameter model for next-edit autocomplete, quantized to Q8_0 GGUF format. Sweep Next-Edit predicts your next code edit before you make it. It runs locally on your laptop in under 500ms (with speculative decoding) and outperforms models over 4x its size on next-edit benchmarks. More details here . uv pip install llama-cpp-python huggingface_hub python run_model.py Model Details Format : GGUF (Q8_0 quantization) Parameters : 1.5B Context Length : 8192 tokens Base Model : Qwen2.5-Coder Example The model uses a specific prompt format with file context, recent diffs, and current state to predict the next edit. See run_model.py for a completefrom huggingface.co
In the maker’s words, at launch
Hey HN, we trained and open-sourced a 1.5B model that predicts your next edits, similar to Cursor. You can download the weights here (https://huggingface.co/sweepai/sweep-next-edit-1.5b) or try it in our JetBrains plugin…
Does a similar job
all alternatives →
I trained a 125M model to autocomplete piano on-deviceAug 2026 · simedw.com · ▲598I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
Code Completion, by Kite2020 · kite.com · ▲90AI-powered autocomplete engine for 13 languages and 16 IDEs
Sweep AI2023 · sweep.dev · ▲8Hi HN, I've been a JetBrains user for the last couple of years, and felt that JetBrains was missing a strong autocomplete tool. Over the last 6 months, we've fine-tuned our own model, built our own inference stack, and integrated it deeply into the IDE. You can use the autocomplete plugin for free (no sign up required) on the JetBrains marketplace. Here's how we got here: We started with standard FIM (fill-in-the-middle) autocomplete. Other AI code completion tools in JetBrains can only "add" code at your cursor position. This can be helpful when writing assert statements in unit tests, but…
Autocomplete Python with Deep Learning2019 · github.com · ▲109A simple neural network for python autocompletion. Contribute to vpj/python_autocomplete development by creating an account on GitHub.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
