alt Hacker NewsAfter having been a happy user of Qwen3.6-27B for a few weeks, due to being away from the hardware, I'm currently forced to use Claude Sonnet 4.6
It is such a downgrade. I don't understand how that's even possible. The thing has so many strongly-held opinions I did not ever ask it for, talking just way too much and generally feeling somehow dumber.
Of course, being significantly larger, it will encode more knowledge, but that doesn't help me when I hate talking to it. And all that on top of the fact that talking with it costs real money.
I wonder what it might be that makes me hate it so much. Maybe because it doesn't see itself as a tool but almost an equal? As if its opinions would have weight.
Qwen too can act like an overeager intern, but if you tell it that it is an idiot, it will drop that ego. Not so much with Claude. In my experience, anyway.
Anyway, point is: full ack on that headline.
Replies
Yep, I daily drive Qwen3.6-27B (including for work), have done pretty much since it came out. IMO it's the only (small-ish, local) model worth using, if you can run it. It might not be as good as Opus at "add X large feature" but I don't want that in a model. I want to do the thinking while it does the typing. And Qwen 3.6 27B is perfectly good at that (while in my experience models like the 35A3B and gemma are significant downgrades)
Plus, I never have to worry about rate limits, quotas, or sitting in a queue during peak time. And I can always see its full thoughts, don't have to worry about where my data is getting sent, and know it can't get secretly nerfed.
Running on 2x 3090, 500-1000tok/s prefill and 60tok/s output at Q6_K_XL with MTP on llama.cpp, 220k tokens context window (starts to get a bit dumb above 160k ish), no KV quantization
> talking just way too much
OMG this is such an annoying property, just shut the hell up please, and be concise.
I suspect that this is an artifact of the thinking property, but please just summarize the thinking process far more concisely, where a single sentence answer is more than sufficient the frontier models seem devoted to going on to a minimum of 5 paragraphs and offering 3-5 new directions.
And requests to please only offer a single step at once, or single option at once, or to even stop eagerly offering future directions is really hard to prompt correctly.
And look, there I did exactly what I was complaining about...
Sonnet is extremely overpriced. It's a good model, but not worth the money Anthropic charges for it.
Funny that coding agents have personalities, including "that colleague" you want to avoid even if you know they're probably quite good at what they do!
If you think about it, they're splitting the power across millions of users. Essentially, these AI companies have YOUR hardware that YOU are paying (them) for in a cabinet at some data center. This means the hardware could easily be run locally for inference for these 'big' models. It's just a problem of dynamics-- RAM is being bought in bulk by these companies through these B200 style cards, instead of sold slowly through the open public markets.
This is likely due to a combination of mass funding for the AI companies, but also they are trying to governmentally restrict which countries get access to these cards so certain countries get a head start. The only way to lock that down is to have them literally locked in their own GPU prisons (data centers). Third reason is it does make it possible to train the models faster by having them in the same data center connected directly. Having them distributed to everyone would slow down training considerably.
The current way to 'own' decent RAM and GPUs right now is through the stock market it seems.
I would not generalize based on experiences with Sonnet. The flagship models (Opus being the claude equivalent) are dramatically better.
There's a model on Huggingface where someone takes Qwen and makes it think Opus style, and that one seems to be decent, not sure if they have the 27B variant in that style. I do wonder if you can tweak your system prompt to force Qwen to behave better?
Curious if you have tried custom instructions. I was never quite as unhappy with Claude's voice as you appear to be, but there were several things I didn't like. A custom prompt fixed almost all of them.
Why would I want some half assed coding assist tool. I want something that takes in a requirement and spits out a finished product. It’s not your equal, it’s better than you.
what kind of hardware do you need in order to run qwen3.6-27b
I noticed Fable was quite a bit terser, and I think it's due to changes in the system prompt [0]. They're literally saying "just give me the TLDR" and "give brief updates". You can tweak a lot of that with an AGENTS.md.
[0] https://twelvetables.blog/comparing-claude-fable-5s-system-p...
Why Sonnet 4.6 not Opus?
Well but comparing with sonnet 4.6 instead of opus 4.6,.7 or .8 doesnt make a real point I mean, pay 200 USD/month (if you have that cash, or your company has it), might not justify using local at all (unless you have some reason to suspect about data leakage)
sync/ack
The Anthropic models have always been annoying this way -- chatty/opinionated and Dunning-Krugerish. And love to run away and do things unprompted with me jamming my ESC ESC ESC key over and over so I can get a word in edgewise.
FWIW Codex/GPT models are way less this way. Maybe to a fault.
I'm setting up my DGX Spark to try Qwen 3.6 27B again, as I'm hearing a lot of good reviews. When I tried it some time ago it was still early for support in llama.cpp.
I haven't spent a dime on cloud inference, so cannot make a direct comparison like you. But I can 100% attest to the fact that Qwen3.6-27B is a very capable local model for coding tasks. Over the last month and a half I've been using it almost daily, either on my M2 Ultra or on my RTX 5090 box. I use it for small mundane tasks at ggml-org [0] - nothing really impressive, but definitely a helpful tool for a maintainer. I think I would be using it much more, if I didn't have to spend a lot of my time on reviewing PRs. Currently, I have a very lightweight harness - the pi agent with everything stripped (`pi -nc --offline`) and a short system prompt [1] to align it a bit with my style. About the generation speed: ~100-150 t/s on the RTX 5090 and ~40 t/s on the Mac. I definitely prefer running it on the RTX machine - it's so much faster. But for the sake of testing and getting wider experience with local configurations, I often run it on the Mac too.
[0] - https://github.com/search?q=%22Assisted-by%22+user%3Aggml-or...
[1] - https://github.com/ggml-org/llama.cpp/blob/master/.pi/gg/SYS...