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

Post by moffkalast » Thu, Jan 22, 2026, 7:36 PM UTC

bradfa wrote: post #102

moffkalast wrote: post #38

Earlier quoted context omitted.

Ingesting multiple code files will take forever in prompt processing without a GPU though, tg will be the least of your worries. Especially when you don't append but change it in random places so caching doesn't work.

A FIM or completion model like this won't have a large prompt and caching doesn't work anyways (per their notes). It'll get maybe a few thousand tokens in a prompt, maximum. For a 1.5B model, you should expect usable CPU-only inference on a modern CPU, like at least hundreds of tokens per second of prefill and tens of tokens per second of generation, which is decently usable in terms of responsiveness.

Post by mijoharas » Thu, Jan 22, 2026, 7:43 PM UTC

cmrdporcupine wrote: post #92

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 c…

Post by norir » Thu, Jan 22, 2026, 8:12 PM UTC

zarzavat wrote: post #75

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.…

I have always said this and had people on HN reply that they don't get much use out of autocomplete, which puzzled me. I'm starting to understand that there are two cultures. Developers who are mostly writing new code get the most benefit from autocomplete and comparatively less from Claude Code. CC is neat but when it attempts to create something from nothing the code is often low quality and needs substantial work.…

Post by KronisLV » Thu, Jan 22, 2026, 8:28 PM UTC

cmrdporcupine wrote: post #89

sitkack wrote: post #76

Earlier quoted context omitted.

I am curious about how both of you think Jetbrains is dropping the ball so much that you are no longer buying the tool. You are still using it but no longer getting updates?

I use free RustRover for my open source work. I have not purchased a (new) license for my commercial work, because I haven't been getting as much value as it since my flow has switched to primarily agentic. Mainly, they're pushing Junie and it just isn't that good or compelling, when faced off against the competition. The key thing for me is that I think they had an opportunity here to really rethink how LLMs could i…

Post by cmrdporcupine » Thu, Jan 22, 2026, 8:56 PM UTC

KronisLV wrote: post #117

cmrdporcupine wrote: post #89

Earlier quoted context omitted.

I use free RustRover for my open source work. I have not purchased a (new) license for my commercial work, because I haven't been getting as much value as it since my flow has switched to primarily agentic. Mainly, they're pushing Junie and it just isn't that good or compelling, when faced off against the competition. The key thing for me is that I think they had an opportunity here to really rethink how LLMs could i…

> I have not purchased a (new) license for my commercial work, because I haven't been getting as much value as it since my flow has switched to primarily agentic. I still buy a personal Ultimate license because I want to see them succeed even if like 80% of my time is spent either in a CLI or Visual Studio Code (for quicker startup and edits), a bit unfortunate that Fleet never got to be really good but oh well.