Earlier quoted context omitted.
I mean there is Mistral?
I mean it’s not competitive at all?
It has been more competitive than any other LLMs by non-US/CN companies. Including Korean and Japanese models in case you want to bring those up.
Qwen3.8-Max: A New Bar for Coding and Cowork
201–210 of 652 posts
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#202Earlier quoted context omitted.
I didn't mention it above, but Laguna S is my other favorite model. I use Qwen a lot more, it's smaller and faster, but I like to switch to Laguna when I feel like I need a "heavy hitter" for certain huge or complex tasks.
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
dgx spark, nvfp4 so I have spare room for KV cache (context)
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#203Earlier quoted context omitted.
Good luck doing that in China?
You can send armed men to your house, or restrict companies in America from using these models. They can also restrict US providers from serving these models. Looking at OpenRouter, there is currently 11 providers for 'DeepSeek V4 Flash 0731' with the only non-US one being Deepseek themselves, which aren't even the cheapest.
> the only non-US one being Deepseek themselves, which aren't even the cheapest.
Interesting.
If I were a western lab, might I be tempted to subsidize at least one faster & cheaper provider for Chinese models to keep even more data from leaving the US?
(I know in this case there can just be more efficient providers, am asking more than speculating)
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#204Earlier quoted context omitted.
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.
yes, but at that point even open weight models are not free. Can someone set up the best open-weight model for free and charge pretty much just for GPU usage+operations+margin for inference? yes. But they would have to keep up with how good the private models are. The bet is private models would sell in a similar way at a premium and invest in staying ahead. Is this bet going to work? no idea, don't shoot the messeng…
> yes, but at that point even open weight models are not free. Can someone set up the best open-weight model for free and charge pretty much just for GPU usage+operations+margin for inference? yes.
Or, the company itself can rent the GPU and host the model of their choice on it.
> But they would have to keep up with how good the private models are.
Why? The whole point of the thread is that the marginal gains of using private models is a fraction of the additional cost of using those private models.
IOW, if you really need that improvement over the open models, you can go ahead and pay it. What we are seeing though is that the improvement in general is barely noticeable but the cost is 4x as much.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#205They'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.
Some advice I got from another HN Mac user was to run local models in energy saver mode. You'll get slightly reduced tokens, but the laptop won't overheat and the fans won't go wild.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#206Earlier quoted context omitted.
I didn't mention it above, but Laguna S is my other favorite model. I use Qwen a lot more, it's smaller and faster, but I like to switch to Laguna when I feel like I need a "heavy hitter" for certain huge or complex tasks.
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
quantized + offload
I have an RX 6700 XT with 12gb vram and 64gb system ram. running dense models like 27b is difficult, but i can run IQ4/IQ5 qwen 122b-a10b or 35b-a3b at ~20tok/s
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#207The visual web development / perceptionbench scores are very promising for image->html flows. Here are some test results. Original designs: https://image.non.io/257dc9cb-9e6b-4e00-8f12-23ea5e073649.we... These are fairly rich, pattern-heavy, nuanced designs. I've asked each to create it as a SPA where the map flows behind it. Opus 5 results: https://html.non.io/opusAcmeBooks Qwen 3.8 max results: https://html.non.io/…
Wow the Opus version is a lot more functional (try clicking some links).
I'm quite surprised at the difference.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#208Earlier 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.
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 use 27B in plan mode and 35B MoE in act mode. I noticed that is the best balance for me for consistent tool calls and intelligent planning. Takes some time to switch, but it's worth it for me.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#209Earlier quoted context omitted.
I have been using Qwen3.6-35B-A3B as my daily driver as well and its been phenomenal when it comes to coding
How do you use a 72GB model as your daily driver locally?
use a quantized version. since it's MoE, what matters is that the 3b parameters that are used for every token fit in gpu vram, the rest can stay in system ram. really great if you don't have unified memory.
Re: Qwen3.8-Max: A New Bar for Coding and Cowork
#210The visual web development / perceptionbench scores are very promising for image->html flows. Here are some test results. Original designs: https://image.non.io/257dc9cb-9e6b-4e00-8f12-23ea5e073649.we... These are fairly rich, pattern-heavy, nuanced designs. I've asked each to create it as a SPA where the map flows behind it. Opus 5 results: https://html.non.io/opusAcmeBooks Qwen 3.8 max results: https://html.non.io/…
Update: Tried using Qwen Desktop. It told me it succeeded, and linked me to the folder it created it in.
That folder didn't exist, I asked Qwen where the files were, and it attempted to create them again.
Stopped it, and asked what happened to the original files. Qwen Desktop apparently doesn't have access to the local file system, but continued merrily along without warning about that.
https://image.non.io/07a153cd-c31c-4f7b-a89d-363faec05a91.we...
