Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen 3.7 Preview

twitter.com

Post reply on HN
Print view View original

31–40 of 100 posts

Re: Qwen 3.7 Preview

#31

Post by Aurornis »

trilogic wrote: post #12

Qwen 3.6 35B (finetuned) is so good that it became standard open weights for everyday use. Is not far at all from proprietary models if you give it tools, skills and agents etc, it can actually finish the job. (Thank you Qwen team, appreciated). Using opensource now we can definitely rely to design from scratch very complicated architecture and build pretty fast the full pack. Wish to see Europe AI unleashed, wake up…

> Is not far at all from proprietary models if you give it tools, skills and agents etc,

I use Qwen 3.6 27B, the dense version of this model which is slightly better.

I don't agree that it's close at all. Maybe for some small, easy tasks, but not for working on real codebases. It's amazing for something I can run at home, but the difference between it and Opus or GPT-5.5 is huge.

Re: Qwen 3.7 Preview

#32

Post by tedivm »

Aurornis wrote: post #31
trilogic wrote: post #12

Qwen 3.6 35B (finetuned) is so good that it became standard open weights for everyday use. Is not far at all from proprietary models if you give it tools, skills and agents etc, it can actually finish the job. (Thank you Qwen team, appreciated). Using opensource now we can definitely rely to design from scratch very complicated architecture and build pretty fast the full pack. Wish to see Europe AI unleashed, wake up…

> Is not far at all from proprietary models if you give it tools, skills and agents etc, I use Qwen 3.6 27B, the dense version of this model which is slightly better. I don't agree that it's close at all. Maybe for some small, easy tasks, but not for working on real codebases. It's amazing for something I can run at home, but the difference between it and Opus or GPT-5.5 is huge.

I've had the opposite experience, and have built multiple fantastic applications with Qwen3.6 27b. What quantization have you tested with?

Re: Qwen 3.7 Preview

#33

Post by hedgehog »

tedivm wrote: post #32
Aurornis wrote: post #31

Earlier quoted context omitted.

> Is not far at all from proprietary models if you give it tools, skills and agents etc, I use Qwen 3.6 27B, the dense version of this model which is slightly better. I don't agree that it's close at all. Maybe for some small, easy tasks, but not for working on real codebases. It's amazing for something I can run at home, but the difference between it and Opus or GPT-5.5 is huge.

I've had the opposite experience, and have built multiple fantastic applications with Qwen3.6 27b. What quantization have you tested with?

Similarly I haven't seen Qwen 27B as remotely competitive with Opus, at least Q4 hooked up to Claude Code. What harness are you using?

Re: Qwen 3.7 Preview

#34

Post by 2001zhaozhao »

tedivm wrote: post #10
rspoerri wrote: post #4

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.

I've completely replaced GitHub Copilot using Sonnet 3.6 with OpenCode using Qwen3.6 27b, and it's been a great experience.

Is Sonnet 3.6 a typo? Claude Sonnet 3.6 (aka 3.5 New) is an ancient model from 2024

Re: Qwen 3.7 Preview

#35

Post by tredre3 »

jwr wrote: post #9
hydra-f wrote: post #7

Vision has become totally underappreciated, whereas I believe it brings important advantages to a model Also, a big caveat in using Qwen models has always been its speech patterns. I do wonder how Google made the Gemma lineup so good at this Let's hope Alibaba continues to open source its models

Agreed. Incidentally, in my testing, qwen models (qwen3.6-35b-a3b and earlier 3.5) are WAY better with vision than gemma4-26b-a4b. I would normally want to stick with gemma4 only (I use it for spam filtering), but it just doesn't cut it for vision work, and qwen models do.

That has been my experience has well.

Qwen 3.5/3.6 are far better at vision. Even the 9B model beats Gemma 4 31B in my use case. They describe the scene more accurately and they focus on the important elements like a human would.

Gemma 4 frequently misses important element, doesn't understand what things are, and is very coy even if you ask for lots of detail. You have to give it hints "hey what's that round thing on the left" to get half decent answers.

(Yes I did set the min-tokens correctly. I also tested bf16 and Q8 to make sure it wasn't a quant issue.)

It's unfortunate because Gemma 4 is so so so much better at natural language interactions.

Re: Qwen 3.7 Preview

#36

Post by trilogic »

Aurornis wrote: post #31
trilogic wrote: post #12

Qwen 3.6 35B (finetuned) is so good that it became standard open weights for everyday use. Is not far at all from proprietary models if you give it tools, skills and agents etc, it can actually finish the job. (Thank you Qwen team, appreciated). Using opensource now we can definitely rely to design from scratch very complicated architecture and build pretty fast the full pack. Wish to see Europe AI unleashed, wake up…

> Is not far at all from proprietary models if you give it tools, skills and agents etc, I use Qwen 3.6 27B, the dense version of this model which is slightly better. I don't agree that it's close at all. Maybe for some small, easy tasks, but not for working on real codebases. It's amazing for something I can run at home, but the difference between it and Opus or GPT-5.5 is huge.

Really, how so? Because we work with codebases daily, can you tell us a concrete example! In our case we work in consumer hardware (ish), 10 million ctx (1 million output, 1 million input proven, sometimes it loops or breaks at over 500k ctx byt at ~17tps linear). IT can read the full codebase, unleash agents, and write in disk editing and patching files creating a full app in 3-4 minutes. IT can do Web search and Rag pretty fast, it understands and fix the user query, sys prompts and adapt/fix them if needed on the fly. I am wondering what more do you do?

Re: Qwen 3.7 Preview

#37

Post by genxy »

sleepyeldrazi wrote: post #28
genxy wrote: post #24

Earlier quoted context omitted.

How good must their training pipelines be? Releasing publicly and at this rate has made them very efficient.

Finetuning takes little resources, the base model training is the slow and expensive part. Architecturally 3.5 models are identical to their 3.6 counterparts, that is why there is a consensus that those are probably finetunes and not re-trained from scratch, like you will se many people publish their own on huggingface.

Understood, but look at their larger cadence over the years and the breadth of models. They are clearly not all finetunes. Meta for all its billions, doesn't have anything comparable.

Re: Qwen 3.7 Preview

#39

Post by trilogic »

trilogic wrote: post #36
Aurornis wrote: post #31

Earlier quoted context omitted.

> Is not far at all from proprietary models if you give it tools, skills and agents etc, I use Qwen 3.6 27B, the dense version of this model which is slightly better. I don't agree that it's close at all. Maybe for some small, easy tasks, but not for working on real codebases. It's amazing for something I can run at home, but the difference between it and Opus or GPT-5.5 is huge.

Really, how so? Because we work with codebases daily, can you tell us a concrete example! In our case we work in consumer hardware (ish), 10 million ctx (1 million output, 1 million input proven, sometimes it loops or breaks at over 500k ctx byt at ~17tps linear). IT can read the full codebase, unleash agents, and write in disk editing and patching files creating a full app in 3-4 minutes. IT can do Web search and Ra…

Edit: Forgot to mention that it can process images and pdf, and 100s of other files, it can even create presentations in code or mermaid, svg, charts js etc. Here a basic version of it: https://hugston.com/chat
Post reply on HN