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

Qwen3.8-Max: A New Bar for Coding and Cowork

qwen.ai

Post reply on HN
Print view View original

121–130 of 652 posts

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#121

Post by lcnPylGDnU4H9OF »

nozzlegear wrote: post #112
tommica wrote: post #104

Earlier quoted context omitted.

What on earth hardwares do you guys have to be able to run 100gb models locally?! That's crazy! I'm here struggling to even get 27b models to run in somewhat usable way

Haha I'm on an Mac Studio with an M1 Ultra, 64gb ram. I bought it when it first came out, it just happens to be good for local LLMs. I have to use a smaller quant of Laguna S though (I think 4-bit? Not at my machine to check), as 8-bit and full size definitely don't fit in the 64gb I have.

Yeah, a good rule of thumb is that the weights take up ~100% of the size of the model, so 100B bytes (8-bit quant) would be, well, 100GB and a 4-bit quant would be half that.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#123

Post by dpc_01234 »

aliljet wrote: post #79

I'm trying and failing to find value running a potential Qwen 3.8 27b dense model on a 16 core, 128 GB of ram, 2080ti box. Yes, the GPU yells for help, but the problem is that no math works to upgrade this machine even when pouring $200 in rent every month into the large model providers... How are you all justifying economical use of these local models right now? What's the cost efficient way to do this and do better…

There's no point, except if you want privacy and independence. I am playing with a personal assistant that checks my emails, calendars, sends me an agenda and maintains my TODO list. I am not sending such data outside.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#124

Post by docheinestages »

It was a matter of time for China to catch up with the US. In terms of infrastructure, manufacturing, and engineering workforce, China has the upperhand and I foresee them becoming the SOTA leaders. Maybe if the US wasn't so busy gatekeeping and keeping things proprietary, they would've had more trust from the open source community.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#125

Post by lelanthran »

twelve40 wrote: post #86
gr_norm wrote: post #66

Earlier quoted context omitted.

Agree, I don't necessarily see a strong argument favoring OpenAI or Anthropic here. In the interest of perspective, can anyone (perhaps playing devil's advocate) give one? The open models are now good enough for what I want to do with them, let alone any future improvements. And factoring in efficiency gains, a model in the ~70b range starting to satisfy my needs would completely obviate the need to pay others for in…

coding on a laptop is only one use case you can't create a new drug by running a model on a laptop. You can't serve a customer support bot running on a laptop. You can't generate video in bulk for many users on a laptop. So there is still a case for paying others for inference. Does it justify the valuations? No idea, but some major use cases are still there. That's why they are rushing to implement, OpenAI creating…

Surely all those use cases can be done right now without a closed model?

I think GP was asking specifically about the use case for closed models.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#126

Post by npodbielski »

nozzlegear wrote: post #61
pettijohn wrote: post #37

Earlier quoted context omitted.

35B MoE is certainly a good and fast local model. I find 27B dense to be quite a bit smarter, so I daily drive that. I wish there was a ~100B MoE with maybe 10B active. It would be super smart and fast!

I've heard 27B is smarter! I tried it some time ago but couldn't get it working with my oMLX. I need to try it again.

In my case I would say they are comparable but moe models are looping and getting lost a lot more than dense models.

On the other hand having 90t/s with any local model is nice and Pi with loop police extension can prevent looping a lot.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#128

Post by t43562 »

usef- wrote: post #64
EMIRELADERO wrote: post #58

Earlier quoted context omitted.

You are right to feel that way about the frontier labs, especially Anthropic. From https://stratechery.com/2026/anthropics-safety-superpower/ > "Anthropic believes that they are the ones who should have final say over how Anthropic is used; given that they think only they should be developing leading edge AI, they by extension think that only they should have final say over AI generally. When you further combine this…

To be fair, we're simultaneously mocking anthropic for believing in safety so much and also for them thinking they're the only ones that care enough about it. It's true that no one else seems to care as much. Judging by reactions from everyone, all their safety talk is very bad PR.

What they believe now or care about is fundamentally not very relevant: allowing them a monopoly would be a big mistake. Google was supposed to do no evil and it probably started that way but nothing guarantees the future other than having alternatives.

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#129

Post by hippycruncher22 »

XCSme wrote: post #41
toshinoriyagi wrote: post #8

They've also announced Qwen3.8-27B being released open-weight next week. Qwen3.6-27B is widely regarded as one of the best local models, especially since nothing else comes close to it, that isn't benchmaxxed, without being significantly larger. If 3.8 truly improves upon it that would be awesome.

If they trained it well, and can do computer use, it will be a new era. Companies can keep PCs, put Qwen 3.8 27b on it and get rid of the employees, lol...

Yes let’s get rid of employees so no one is employed but somehow they can afford to buy my stuff

Re: Qwen3.8-Max: A New Bar for Coding and Cowork

#130

Post by jbellis »

aliljet wrote: post #79

I'm trying and failing to find value running a potential Qwen 3.8 27b dense model on a 16 core, 128 GB of ram, 2080ti box. Yes, the GPU yells for help, but the problem is that no math works to upgrade this machine even when pouring $200 in rent every month into the large model providers... How are you all justifying economical use of these local models right now? What's the cost efficient way to do this and do better…

The only scenario is if you have enough work to do batch inference. Using a tiny fraction of GPU capacity to decode a single request at a time just doesn't make sense, as you say.
Post reply on HN