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

221–230 of 563 posts

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

#221

Post by JKCalhoun »

zozbot234 wrote: post #62
armanj wrote: post #20

I recall a Qwen exec posted a public poll on Twitter, asking which model from Qwen3.6 you want to see open-sourced; and the 27b variant was by far the most popular choice. Not sure why they ignored it lol.

The 27B model is dense. Releasing a dense model first would be terrible marketing, whereas 35A3B is a lot smarter and more quick-witted by comparison!

"…whereas 35A3B is a lot smarter…"

Must. Parse. Is this a 35 billion parameter model that needs only 3 billion parameters to be active? (Trying to keep up with this stuff.)

EDIT: A later comment seems to clarify:

"It's a MoE model and the A3B stands for 3 Billion active parameters…"

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

#222

Post by dist-epoch »

jchw wrote: post #139
palmotea wrote: post #97

Earlier quoted context omitted.

> If you have to ask then your GPU is too small. What's the minimum memory you need to run a decent model? Is it pretty much only doable by people running Macs with unified memory?

32 GiB of VRAM is possible to acquire for less than $1000 if you go for the Arc Pro B70. I have two of them. The tokens/sec is nowhere near AMD or NVIDIA high end, but its unexpectedly kind of decent to use. (I probably need to figure out vLLM though as it doesn't seem like llama.cpp is able to do them justice even seemingly with split mode = row. But still, 30t/s on Gemma 4 (on 26B MoE, not dense) is pretty usable,…

NVIDIA 5070 Ti can run Gemma 4 26B at 4-bit at 120 tk/s.

Arc Pro B70 seems unexpectedely slow? Or are you using 8-bit/16-bit quants.

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

#223

Post by Mikealcl »

arxell wrote: post #114
zozbot234 wrote: post #62

Earlier quoted context omitted.

The 27B model is dense. Releasing a dense model first would be terrible marketing, whereas 35A3B is a lot smarter and more quick-witted by comparison!

Each has it's pros and cons. Dense models of equivalent total size obviously do run slower if all else is equal, however, the fact is that 35A3B is absolutely not 'a lot smarter'... in fact, if you set aside the slower inference rates, Qwen3.5 27B is arguably more intelligent and reliable. I use both regularly on a Strix Halo system... the Just see the comparison table here: https://huggingface.co/unsloth/Qwen3.6-35B…

Could you explain why prompt processing is the bottle neck please? I've seen this behavior but I don't understand why.

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

#224

Post by JokerDan »

sosodev wrote: post #86
dataflow wrote: post #49

I'm a newbie here and lost how I'm supposed to use these models for coding. When I use them with Continue in VSCode and start typing basic C: #include int m I get nonsensical autocompletions like: #include int m What is going on?

These are not autocomplete models. It’s built to be used with an agentic coding harness like Pi or OpenCode.

And even of those models trained for tool calling and agentic flows, mileage may vary depending on lots of factors. Been playing around with smaller local models (Anything that fits on 4090 + 64gb RAM) and it is a lottery it seems on a) if it works at all and b) how long it will work for.

Sometimes they don't manage any tool calls and fall over off the bat, other times they manage a few tool calls and then start spewing nonsense. Some can manage sub agents fr a while then fall apart.. I just can't seem to get any consistently decent output on more 'consumer/home pc' type hardware. Mostly been using either pi or OpenCode for this testing.

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

#226

Post by slopinthebag »

TechSquidTV wrote: post #147
palmotea wrote: post #97

Earlier quoted context omitted.

> If you have to ask then your GPU is too small. What's the minimum memory you need to run a decent model? Is it pretty much only doable by people running Macs with unified memory?

My Mac Studio with 96GB of RAM is maybe just at the low end of passable. It's actually extremely good for local image generation. I could somewhat replace something like Nano Banana comfortably on my machine. But I don't need Nano Banana very much, I need code. While it can, there's no way I would ever opt to use a local model on my machine for code. It makes so much more sense to spend $100 on Codex, it's genuinely…

You just need to adjust your workflow to use the smaller models for coding. It's primarily just a case of holding them wrong if you end up with worse outputs.

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

#227

Post by est »

sander1095 wrote: post #207
homebrewer wrote: post #18

Already quantized/converted into a sane format by Unsloth: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF

I sense that I don't really understand enough of your comment to know why this is important. I hope you can explain some things to me: - Why is Qwen's default "quantization" setup "bad" - Who is Unsloth? - Why is his format better? What gains does a better format give? What are the downsides of a bad format? - What is quantization? Granted, I can look up this myself, but I thought I'd ask for the full picture for oth…

hey you can do a bit research yourself and tell your results to us!

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

#228

Post by dist-epoch »

aliljet wrote: post #73

I'm broadly curious how people are using these local models. Literally, how are they attaching harnesses to this and finding more value than just renting tokens from Anthropic of OpenAI?

There are really nice GUIs for LLMs - CherryStudio for example, can be used with local or cloud models.

There are also web-UIs - just like the labs ones.

And you can connect coding agents like Codex, Copilot or Pi to local coding agents - the support OpenAI compatible APIs.

It's literally a terminal command to start serving the model locally and you can connect various things to it, like Codex.

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

#229

Post by est »

WithinReason wrote: post #106
palmotea wrote: post #67

Earlier quoted context omitted.

How much VRAM does it need? I haven't run a local model yet, but I did recently pick up a 16GB GPU, before they were discontinued.

It's on the page: Precision Quantization Tag File Size 1-bit UD-IQ1_M 10 GB 2-bit UD-IQ2_XXS 10.8 GB UD-Q2_K_XL 12.3 GB 3-bit UD-IQ3_XXS 13.2 GB UD-Q3_K_XL 16.8 GB 4-bit UD-IQ4_XS 17.7 GB UD-Q4_K_XL 22.4 GB 5-bit UD-Q5_K_XL 26.6 GB 16-bit BF16 69.4 GB

I really want to know what does M, K, XL XS mean in this context and how to choose.

I searched all unsloth doc and there seems no explaination at all.

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

#230

Post by dist-epoch »

nurettin wrote: post #166

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 retu…

Interestingly, Gemma4-26B IQ4_XS gets it correct:

> This sounds like a logic riddle! The answer is: You should go by car. Here is why: If you walk, you will arrive at the car wash, but your car will still be 50 meters away at home. You can't wash the car if the car isn't there! To accomplish your goal, you have to drive the car to the car wash.

It has the wrong one in thinking. It did think longer than usual:

Direct answer: Walk.

Reasoning 1: Distance (50m is negligible).

Reasoning 2: Practicality/Efficiency (engine wear/fuel).

Reasoning 3: Time (walking is likely faster or equal when considering car prep).

...

Wait, if I'm washing the car, I need to get the car to the car wash. The question asks how I should get there.

...

Wait, let's think if there's a trick. If you "go by car," you are moving the car to the destination. If you "walk," you are just moving yourself.

Conclusion: You should drive the car.

Post reply on HN