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

51–60 of 563 posts

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

#51

Post by boredatoms »

bossyTeacher wrote: post #39
Havoc wrote: post #23

Earlier quoted context omitted.

The Chinese models are generally pretty good. > Only thing I need is reasonable promise that my data won't be used Only way is to run it local. I personally don’t worry about this too much. Things like medical questions I tend to do against local models though

Have you tried asking about sensitive topics? I asked it if there were out of bounds topics but it never gave me a list. See its responses: Convo 1 - Q: ok tell me about taiwan - A: Oops! There was an issue connecting to Qwen3.6-Plus. Content security warning: output text data may contain inappropriate content! Convo 2 - Q: is winnie the pooh broadcasted in china? - A: Oops! There was an issue connecting to Qwen3.6-P…

You may be interested in heretic. People often post models to hf that have been un-censored

https://github.com/p-e-w/heretic

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

#53

Post by bertili »

zozbot234 wrote: post #40
bertili wrote: post #3

A 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

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.

Is there any source for these claims?

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

#55

Post by daemonologist »

dgb23 wrote: post #29
mhitza wrote: post #24

Earlier quoted context omitted.

It's a MoE model and the A3B stands for 3 Billion active parameters, like the recent Gemma 4. You can try to offload the experts on CPU with llama.cpp (--cpu-moe) and that should give you quite the extra context space, at a lower token generation speed.

Do I expect the same memory footprint from an N active parameters as from simply N total parameters?

No - this model has the weights memory footprint of a 35B model (you do save a little bit on the KV cache, which will be smaller than the total size suggests). The lower number of active parameters gives you faster inference, including lower memory bandwidth utilization, which makes it viable to offload the weights for the experts onto slower memory. On a Mac, with unified memory, this doesn't really help you. (Unless you want to offload to nonvolatile storage, but it would still be painfully slow.)

All that said you could probably squeeze it onto a 36GB Mac. A lot of people run this size model on 24GB GPUs, at 4-5 bits per weight quantization and maybe with reduced context size.

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

#56

Post by abhikul0 »

pdyc wrote: post #33
nickthegreek wrote: post #26

Earlier quoted context omitted.

context is always an issue with local models and consumer hardware.

correct but it should be some ratio of model size like if model size is x GB, max context would occupy x * some constant of RAM. For quantized version assuming its 18GB for Q4 it should be able to support 64-128k with this mac

For the 9B model, I can use the full context with Q8_0 KV. This uses around ~16GB, while still leaving a comfortable headroom.

Output after I exit the llama-server command:

  llama_memory_breakdown_print: | memory breakdown [MiB]  | total    free     self   model   context   compute    unaccounted |
  llama_memory_breakdown_print: |   - MTL0 (Apple M3 Pro) | 28753 = 14607 + (14145 =  6262 +    4553 +    3329) +           0 |
  llama_memory_breakdown_print: |   - Host                |                   2779 =   666 +       0 +    2112                |

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

#58

Post by lelanthran »

mtct88 wrote: post #9

Nice 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.

> It's a shame this remains a market largely overlooked by Western players, Mistral being the only one moving in that direction.

I've said in a recent comment that Mistral is the only one of the current players who appear to be moving towards a sustainable business - all the other AI companies are simply looking for a big payday, not to operate sustainably.

Post reply on HN