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

Qwen3.6-35B-A3B: Agentic coding power, now open to all

qwen.ai

Post reply on HN
Print view View original

261–270 of 563 posts

Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all

#261

Post by rexreed »

999900000999 wrote: post #219

Looking to move off ollama on Open Suse tumbleweed. Should I use brew to install llma.ccp or the zypper to install the tumbleweed package?

Why are you looking to move off Ollama? Just curious because I'm using Ollama and the cloud models (Kimi 2.5 and Minimax 2.7) which I'm having lots of good success with.

Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all

#264

Post by DiabloD3 »

psim1 wrote: post #253

(Please don't downvote - serious question) Are Chinese models generally accepted for use within US companies? The company I work for won't allow Qwen.

There is a difference between Chinese model and Chinese service.

Your company most likely is banning the use of foreign services, but it wouldn't make sense to ban the model, since the model would be ran locally.

I wouldn't allow my employees to use a foreign service either if my company had specific geographic laws it had to follow (ie, fin or med or privacy laws, such as the ones in the EU).

That said, I'm not sure I'd allow them to use any AI product either, locally inferred on-prem or not: I need my employees to _not_ make mistakes, not automate mistake making.

Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all

#265

Post by andrewmcwatters »

tristor wrote: post #126
adrian_b wrote: post #120

Earlier quoted context omitted.

You are right, but this is just the first open-weights model of this family. They said that they will release several open-weights models, though there was an implication that they might not release the biggest models.

I'm totally fine with that, frankly. I'm blessed with 128GB of Unified Memory to run local models, but that's still tiny in comparison the larger frontier models. I'd much rather get a full array of small and medium sized models, and building useful things within the limits of smaller models is more interesting to me anyway.

[dead]

Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all

#266

Post by KronisLV »

I wonder how this one compares to Qwen3 Coder Next (the 80B A3B model), since you'd think that even though it's older, it having more parameters would make it more useful for agentic and development use cases: https://huggingface.co/collections/Qwen/qwen3-coder-next

Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all

#267

Post by parsimo2010 »

r-w wrote: post #255
kylehotchkiss wrote: post #252

Earlier quoted context omitted.

How many people/hackernews can run a 397b param model at home? Probably like 20-30.

OpenRouter.

If you're running it from OpenRouter, you might as well use Qwen3.6 Plus. You don't need to be picky about a particular model size of 3.6. If you just want the 397b version to save money, just pick a cheaper model like M2.7.

Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all

#269

Post by stavros »

kylehotchkiss wrote: post #252
zozbot234 wrote: post #40

Earlier quoted context omitted.

This is just one model in the Qwen 3.6 series. They will most likely release the other small sizes (not much sense in keeping them proprietary) and perhaps their 122A10B size also, but the flagship 397A17B size seems to have been excluded.

How many people/hackernews can run a 397b param model at home? Probably like 20-30.

It doesn't matter how many can run it now, it's about freedom. Having a large open weights model available allows you to do things you can't do with closed models.
Post reply on HN