Qwen 3.7 Preview

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

still waiting for a update to Qwen3-Coder-Next

That would be nice, but it's not going to be possible.

Any open benchmark has a very short life, since it will be pulled in and DPO / RL trained quickly for benchmaxxing purposes. So, you'll need a private test to have a hope of something fair. (These also get leaked over time, btw, so even then there's a window of usability).

These are expensive to run.

Now consider that there might be 15-20 viable quants for a given open model release; someone would have to want to pay for these private evals to be run on them. Even then, a good read through unsloth's commits and blog posts will remind you that there's quite a lot of engineering work to be done to get model inference working properly, even for models released by frontier or near-frontier labs. So, you'd want to make sure that you have a replicable 'best engineered' deployment to evaluate, or at least one that's closest to your hardware and fits the bill.

Upshot - it's much faster to download and try out a model, and possibly cheaper too. Well, cheaper since hugging face is paying the bandwidth bills.

>I just want to know what the best model is. Let me worry about how I will afford to run it.

This is a very typical manager question that I suppose many people have who fail to see the simple truth: There is no "best" model. There are only best models for certain use-cases. Sometimes you'll find these in custom community leaderboards on platforms like huggingface, but for most business applications you'll probably have to come up with your own benchmark. Most common benchmarks are pretty worthless by now because all the usual ones are being gamed hard by model providers, to the point that there are now sometimes drastic differences between models that perform very similarly on common benchmarks.

The best thing I have come up with is just make a bunch of prompts / tasks that I personally care about and need a model to know how to do. As an example, when qwen3.6 27B dropped, I ran it, kimi, claude and glm 5/5.1 on a bunch of LLM-architecture specific tasks (stuff like 'implement an incremental KV-cache for autoregressive transformer inference' or 'implement flash Attention backward pass with D-optimization') and analyze the results, who made tests, are the tests valid, does their implementation actually work or are they only claiming it to, that sort of thing.

It is a day/weekend worth of work, but I think this is the best way to determine if the model fits your need specifically. This is what lead me to finding out that qwen 27b outperformed even kimi on those tasks, and that opus tries gaslighting me when I give it a spec of something that has been proven, but no published solution exists online. All other models gave their best shot at solving it, opus just said it's not possible (even when I gave it the finished working product that obviously works).

Especially for small models (but also big ones) I think the only way to know if a model will improve your workflow is this, personal benchmarks, expanded over time, ran in private.

> Ideally I would love to see a leaderboard with relatively objective ranking criteria that 1. lets you filter by open weight / locally runnable, 2. filter by date of release (nothing older than x), and 3. is agnostic to hardware requirements. I just want to know what the best model is. Let me worry about how I will afford to run it.

Stick to artificialanalysis.ai it has become the norm

benchmarks = bs

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.

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.

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.

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.

Since you are using unsloth models from HF, why not use Unsloth Studio instead of Ollama?

It is supposed to be faster + they will update the new models multiple times during the first month to correct bugs and performance issues

https://unsloth.ai/docs/new/studio#quickstart

I have a much more powerful PC and I would not call Qwen3-Coder-30B-A3B "fast" on my machine by any stretch of the word. How are you running it?

What are your use cases?

> 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.

It's 3.7-max; max was never open-weighted before. I don't see any smaller models in that tweet.

For coding it’s really bad. Writing is ok, chat is good. It’ll get better but it’s not that close yet

Do you have a good resource on how to finetune a model like Qwen? I am curious to try it out.

Can you share the GGUF for this specific success story? I'd like to try it for myself.

Just to be clear, "Plus" and "Max" Qwen models are closed. Seems likely smaller open versions will be released, but that's not what was announced today

To play devil's advocate I do feel like Grok has a unique "feel" to it. All the Chinese models feel like GPT or Claude distillations, but Grok has a certain unique way of saying and doing things. But that said, it also feels a year behind the state of the art.

Would xAI do this if Grok was competitive?

https://www.nytimes.com/2026/04/03/business/spacex-ipo-grok-...

Of course they will.

Right now they want to prevent the US labs from gaining any sort of self-reinforcing oligopoly on the space, and to let the ecosystem in China flourish.

That will all die sooner or later.

Run locally and you can now do it on an airplane

There's a Grok 4.20 at #10? Maybe they just skipped version numbers for the 420 luls (are we 15 or what? wtf)

88th

They made it less sycophantic. Which is a good thing for mental health, but maybe a bad thing for popularity contests.