alt Hacker NewsQwen3.6-35B-A3B: Agentic coding power, now open to all
Comments
I'm disappointed they didn't release a 27B dense model. I've been working with Qwen3.5-27B and Qwen3.5-35B-A3B locally, both in their native weights and the versions the community distilled from Opus 4.6 (Qwopus), and I have found I generally get higher quality outputs from the 27B dense model than the 35B-A3B MOE model. My basic conclusion was that MoE approach may be more memory efficient, but it requires a fairly large set of active parameters to match similarly sized dense models, as I was able to see better or comparable results from Qwen3.5-122B-A10B as I got from Qwen3.5-27B, however at a slower generation speed. I am certain that for frontier providers with massive compute that MoE represents a meaningful efficiency gain with similar quality, but for running models locally I still prefer medium sized dense models.
I'll give this a try, but I would be surprised if it outperforms Qwen3.5-27B.
Does 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.
[dead]
[dead]
[dead]
[dead]
[dead]
[dead]
[dead]
[dead]
I don't want "Agentic Power".
I want to reduce AI to zero. Granted, this is an impossible to win fight, but I feel like Don Quichotte here. Rather than windmill-dragons, it is some skynet 6.0 blob.
More benchmaxxing I see. Too bad there’s no rig with 256gb unified ram for under $1000
I tried the car wash puzzle:
You want to wash your car. Car wash is 50m away. Should you walk or go by car?
> Walk. At 50 meters, the round trip is roughly 100 meters, taking about two minutes on foot. Driving would require starting the engine, navigating, parking, and dealing with unnecessary wear for a negligible distance. Walk to the car wash, and if the bay requires the vehicle inside, have it moved there or return on foot. Walking is faster and more efficient.
Classic response. It was really hard to one shot this with Qwen3.5 Q4_K_M.
Qwen3.6 UD-IQ4_XS also failed the first time, then I added this to the system prompt:
> Double check your logic for errors
Then I created a new dialog and asked the puzzle and it responded:
> Drive it. The car needs to be present to be washed. 50 meters is roughly a 1-minute walk or a 10-second drive. Walking leaves the car behind, making the wash impossible. Driving it the short distance is the only option that achieves the goal.
Now 3.6 gets it right every time. So not as great as a super model, but definitely an improvement.