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

341–350 of 652 posts

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

#341

Post by freehorse »

tsss wrote: post #330
leansensei wrote: post #278

Earlier quoted context omitted.

Huh what? Qwen3.5-35B-A3B runs just fine with maximum context, on an RTX SUPER 12 GB, with offloading of some expert layers to DDR4-3200. Same story on an RTX 4060 Ti 16 GB. MTP is a serious boost to tg. Downloading the model is a simple hf command that HuggingFace's web UI even gives you. llama.cpp is trivial to use, and so is llama-swap, if you want to use other models too. If you don't know what arguments to run i…

RTX Super 12GB costs $700. An openrouter account costs nothing.

A lot of people already have 12GB+ GPUs lying around for playing games, doing video editing, etc. I would not get a GPU or mac just to run LLMs personally, but if one wants to get such a device for other tasks too, it may make sense to eg choose a slightly higher (v)RAM variant if they want to run some bigger models. Then what you pay for the local llms is just the difference.

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

#342

Post by gcr »

me551ah wrote: post #257

This makes me wonder if AI companies even have a MOAT in the first place. All requests to an LLM are idempotent, for every API call you need to send it the entire conversation history so that it can process it. LLMs do not learn or remember anything, which makes it super easy for users to switch LLMs on the fly. Most popular AI frameworks, make this a one-liner change these days. And that makes me wonder if the trill…

This isn’t technically true. Most model providers don’t send the thinking tokens anymore, so if you switch from one provider to another, you will be missing large parts of the conversation.

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

#344

Post by Tryk »

stanac wrote: post #243
markasoftware wrote: post #197

Earlier quoted context omitted.

Moonshot is printing money on k3. It likely costs the same to serve as qwen3.8. The license requires all major inference providers to sign an extra (secret) licensing agreement with moonshot that almost certainly requires them to agree to this price and pay royalties to moonshot. Watch as the k3 price plummets over the next 1-2 weeks.

If k3 is open-weight (and it's available on hugging face [1]), how could they force providers to sing an extra (secret) licensing agreement? Edit to answer my own question: License file [2] states: > If the Licensee or any of its affiliates operates a Model as a Service business, and the aggregate revenue of the Licensee and its affiliates exceeds 20 million US dollars (or the equivalent in other currencies) in total…

How would that ever be enforced, I wonder.

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

#345

Post by gcr »

msdz wrote: post #333
whage wrote: post #322

Earlier quoted context omitted.

Can you please explain why?

Not who you responded to, but I’ll give it a try. Imagine our LLM as this one-dimensional matrix (instead of unfathomably many, many more dimensions): 0.728201017 -1.9293839303 2.93020202929 5.82290101728 -0.2844920917 … And then, all of these values are multiplied by some scaling factor, essentially vectors pointing in some direction (in our case, only on a one-dimensional line instead of in some higher-dimensional…

This is oversimplified. The proposed question is whether a model with fewer parameters could achieve performance on one language similar to that of a larger model that’s been trained more broadly, which isn’t straightforward to do.

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

#346

Post by Anonyneko »

leansensei wrote: post #278
jiggawatts wrote: post #249

Earlier quoted context omitted.

This is the diametric opposite of the rent-vs-buy scenario that this entails. Local: You need to invest $thousands into GPU and/or very-high-end CPU+Memory hardware. Vendor: You can use any existing device, even a phone or tablet. A very low-end laptop is fine. > takes literal minutes to get started Local: Typical scenario is hours just to download the software, the model weights, and then faffing around with CUDA an…

Huh what? Qwen3.5-35B-A3B runs just fine with maximum context, on an RTX SUPER 12 GB, with offloading of some expert layers to DDR4-3200. Same story on an RTX 4060 Ti 16 GB. MTP is a serious boost to tg. Downloading the model is a simple hf command that HuggingFace's web UI even gives you. llama.cpp is trivial to use, and so is llama-swap, if you want to use other models too. If you don't know what arguments to run i…

Full model or a 4-bit quant? I have a 5090 and I'm not sure whether I should use a quant that fits within the VRAM or a much bigger version where I'd have to offload a lot to 64GB RAM and a beefy CPU (but still a CPU)

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

#347

Post by quanto »

nozzlegear wrote: post #27
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.

Qwen3.6-35B is my daily driver for AI, and what convinced me to cancel my Claude subscription back in April. The Qwen3.6 line is easily the best local model I've tried, and I've tried a lot. I've got it diligently grinding away on my laptop right now, reviewing and fixing some bugs in my F# code.

Is your Qwen3.6 locally run on your laptop? What kind of tokens/s are you getting from your laptop GPU?

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

#348

Post by enraged_camel »

OtomotO wrote: post #297
websap wrote: post #291

Earlier quoted context omitted.

Needs 0 investment and 0 committment? - You at least need a capable machine, so that's not 0 monetary investment. - You need to spend at least an hour decicding between ollama, llamacp, mlx, etc. - You need to find the correct quantized version of the model that works for you based on the architecture. - You need to figure out the correct context window size to get reasonable performance. - You need to setup a harnes…

> You at least need a capable machine, so that's not 0 monetary investment It is 0 monetary investment if I already have said machine lying around doing nothing. Which is exactly the story OP talked about.

But most people don't have an RTX 5090 lying around, so the story doesn't apply to them, right?

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

#349

Post by anon373839 »

usef- wrote: post #109
red_green_yell wrote: post #103

Earlier quoted context omitted.

The criticism isn't that they believe in safety too much. It's that they patently using safety as a red herring with the actual goal of regulating away competition that they know the cannot beat.

The people involved have been talking about safety long before they had any users or a company. "Concrete Problems in AI Safety" by Dario and another founder was published 2016, anthropic was founded 2021. Among a bunch of other examples, including other founders. If safety is seen as a joke now, it was really seen as a joke back then. The reason they keep shooting themselves in the foot with bad PR is because they t…

I’m sorry, but this do-gooder concept doesn’t jibe with their other actions. For example, swindling their business partners (such as Figma). Filing an unnecessary trademark lawsuit against a customer whose brand predates Anthropic.

And for safety? Oh yeah, they literally sell the removal of guardrails in exchange for minimum spend commitments.

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

#350

Post by saagarjha »

quanto wrote: post #347
nozzlegear wrote: post #27

Earlier quoted context omitted.

Qwen3.6-35B is my daily driver for AI, and what convinced me to cancel my Claude subscription back in April. The Qwen3.6 line is easily the best local model I've tried, and I've tried a lot. I've got it diligently grinding away on my laptop right now, reviewing and fixing some bugs in my F# code.

Is your Qwen3.6 locally run on your laptop? What kind of tokens/s are you getting from your laptop GPU?

I have Qwen3.6 35B-A3B on my laptop and it does 60 tokens/s
Post reply on HN