Hacker News new | ask | show | jobs
by rspoerri 32 days ago
I am very interested in seeing new qwen models. Qwen3.6 27b is the first one that can do things and doesnt constantly loose "it's mind" and that can be run on a 3090 with a good context size. But it's sometimes getting into a loop.
4 comments

Look on HuggingFace, there is a template that is supposed to fix the updates for the Qwen Models.

https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates

Maybe will help you?

I've completely replaced GitHub Copilot using Sonnet 3.6 with OpenCode using Qwen3.6 27b, and it's been a great experience.
Similar, but I'm using 35B A3B variation with experimental MTP support

OpenCode is pretty good too

A3B is especially nice, MoE really shines on memory bandwidth contained platforms like the DGX Spark.
looks like MTP support has now been merged and also updated unsloth quants to go with it (not just the extras, all of 'em!)
Is Sonnet 3.6 a typo? Claude Sonnet 3.6 (aka 3.5 New) is an ancient model from 2024
Pretty sure they meant 4.6
Yeah that was a typo, I meant 4.6.
I sort of thought this about qwen3.5 35b, finally a local model that isn't a complete waste of electricity, but "upgrading" to 3.6 35b left me disappointed. It seemed more like a downgrade. But honestly I've barely used either. Subjectively they still seem far from the frontier models, but for what they can do, it's great to be able to do locally.
How are they just for chat / questions?
Pretty decent, it's given similar book recommendations as Claude when I feed it my list of read books and thoughts on them. You'll have to tell them to never use emojis. I was using 3.5 a while ago to generate some flavor text while I was playing a bit of an old-school dungeon-crawler game (it's like Wizardry), a genre I don't particularly enjoy much, but it's funner with the flavor text. Worth setting up something like open webui or other front-ends since a pure CLI experience via ollama is pretty bad.
I had a flavor of an older version of Qwen (I forget which one to be fair) that was coding along, then lost itself in a loop, I was so confused, it was just a random greenfield "lets see how it does" type of project anyway.