"open source"
give me the training data?
Qwen3.6-35B-A3B: Agentic coding power, now open to all
31–40 of 563 posts
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#32I hope the other sizes are coming too(9B for me). Can't fit much context with this on a 36GB mac.
can you elaborate? you can use quantized version, would context still be an issue with it?
A usable quant, Q5_KM imo, takes up ~26GB[0], which leaves around ~6-7GB for context and running other programs which is not much.
[0] https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF?show_fil...
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#33Earlier quoted context omitted.
can you elaborate? you can use quantized version, would context still be an issue with it?
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
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#34Earlier 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.
i dont get it, mac has unified memory how would offloading experts to cpu help?
I bet the poster just didn’t remember that important detail about Macs, it is kind of unusual from a normal computer point of view.
I wonder though, do Macs have swap, coupled unused experts be offloaded to swap?
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#35Does anyone have any experience with Qwen or any non-Western LLMs? It's hard to get a feel out there with all the doomerists and grifters shouting. Only thing I need is reasonable promise that my data won't be used for training or at least some of it won't. Being able to export conversations in bulk would be helpful.
> Does anyone have any experience with Qwen or any non-Western LLMs? I use GLM-5.1 for coding hobby project, that going to end up on github anyway. Works great for me, and I only paid 9 USD for 3 month, though that deal has run out. > my data won't be used for training Yeah, I don't know. Doubt it.
$20 for 3 months is still far better than alternatives, and 5.1 works great
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#36I hope the other sizes are coming too(9B for me). Can't fit much context with this on a 36GB mac.
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.
Mac has unified memory, so 36GB is 36GB for everything- gpu,cpu.
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#37How does this compare to the commercial models like Sonnet 4.5 or GPT? Close enough that the price is right (free)?
I think its worth noting that if you are paying for electricity Local LLM is NOT free. In most cases you will find that Haiku is cheaper, faster, and better than anything that will run on your local machine.
Electricity (on continental US) is pretty cheap assuming you already have the hardware:
Running at a full load of 1000W for every second of the year, for a model that produces 100 tps at 16 cents per kWh, is $1200 USD.
The same amount of tokens would cost at least $3,150 USD on current Claude Haiku 3.5 pricing.
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#38Nice 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.
How true is this? How does a regulated industry confirm the model itself wasn't trained with malicious intent?
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#39Does anyone have any experience with Qwen or any non-Western LLMs? It's hard to get a feel out there with all the doomerists and grifters shouting. Only thing I need is reasonable promise that my data won't be used for training or at least some of it won't. Being able to export conversations in bulk would be helpful.
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-Plus. Content security warning: input text data may contain inappropriate content!
These seem pretty bad to me. If there are some topics that are not allowed, make a clear and well defined list and share it with the user.
Re: Qwen3.6-35B-A3B: Agentic coding power, now open to all
#40A 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.