Qwen3.6-35B-A3B: Agentic coding power, now open to all
1–10 of 563 posts
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#2Wowzers, we were worried Qwen was going to suffer having lost several high profile people on the team but that's a huge drop.
It's better than 27b?
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#3A relief to see the Qwen team still publishing open weights, after the kneecapping [1] and departures of Junyang Lin and others [2]!
[1] https://news.ycombinator.com/item?id=47246746 [2] https://news.ycombinator.com/item?id=47249343
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#4How does this compare to the commercial models like Sonnet 4.5 or GPT? Close enough that the price is right (free)?
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#5Honestly, this is the AI software I actually look forward to seeing. No hype about it being too dangerous to release. No IPO pumping hype. No subscription fees. I am so pumped to try this!
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#6Available for download:
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#7I hope the other sizes are coming too(9B for me). Can't fit much context with this on a 36GB mac.
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#8More benchmaxxing I see. Too bad there’s no rig with 256gb unified ram for under $1000
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#9Nice release from the Qwen team.
Small openweight coding models are, imho, the way to go for custom agents tailored to the specific needs of dev shops that are restricted from accessing public models.
I'm thinking about banking and healthcare sector development agencies, for example.
It's a shame this remains a market largely overlooked by Western players, Mistral being the only one moving in that direction.
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#10How does this compare to the commercial models like Sonnet 4.5 or GPT? Close enough that the price is right (free)?
The will not measure up. Notice they're comparing it to Gemma, Google's open weight model, not to Gemini, Sonnet, or GPT. That's fine - this is a tiny model.
If you want something closer to the frontier models, Qwen3.6-Plus (not open) is doing quite well[1] (I've not tested it extensively personally):