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

411–420 of 563 posts

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

#411

Post by agentifysh »

3836293648 wrote: post #374

Qwen3.6 and Gemma4 have the same issue of never getting to the point and just getting stuck in never ending repeating thought loops. Qwen3.5 is still the best local model that works.

I think the hype around Qwen and even Gemma4 often floated for views/attention glosses over that these models have clear gaps behind what closed models offer.

In short, it has its uses but it would/should not be the main driver. Will it get better, I'm sure of it, but there is too much hype and exaggeration over open source models, for one the hardware simply isn't enough at a price point where we can run something that can seriously compete with today's closed models.

If we got something like GPT-5.4-xhigh that can run on some local hardware under 5k, that would be a major milestone.

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

#413

Post by realityfactchex »

simonw wrote: post #270

I've been running this on my laptop with the Unsloth 20.9GB GGUF in LM Studio: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF/blob/mai... It drew a better pelican riding a bicycle than Opus 4.7 did! https://simonwillison.net/2026/Apr/16/qwen-beats-opus/

Here's a reproduction attempt (LM Studio, same Qwen3.6-35B-A3B-GGUF model as linked in parent, M1 Max 64GB, https://files.catbox.moe/r3oru2.png

- My Qwen 3.6 result had sun and cloud in sky, similar to the second Opus 4.7 result in Simon's post.

- My Qwen 3.6 result had no grass (except as a green line), but all three results in Simon's post had grass (thick).

- My Qwen 3.6 result had visible "tailing air motion" like Simon's Qwen 3.6 result.

- My Qwen 3.6 result had a "sun with halo" effect that none of Simon's results had.

But, I know, it's more about the pelican and the bicycle.

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

#414

Post by FuckButtons »

zozbot234 wrote: post #236
Mikealcl wrote: post #223

Earlier quoted context omitted.

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

You should be able to save a lot on prefill by stashing KV-cache shared prefixes (since KV-cache for plain transformers is an append-only structure) to near-line bulk storage and fetching them in as needed. Not sure why local AI engines don't do this already since it's a natural extension of session save/restore and what's usually called prompt caching.

if I understand you correctly, this is essentially what vllm does with their paged cache, if I’ve misunderstood I apologize.

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

#415

Post by solomatov »

danielhanchen wrote: post #198
Aurornis wrote: post #176

Earlier quoted context omitted.

Unsloth is great for uploading quants quickly to experiment with, but everyone should know that they almost always revise their quants after testing. If you download the release day quants with a tool that doesn’t automatically check HF for new versions you should check back again in a week to look for updated versions. Some times the launch day quantizations have major problems which leads to early adopters dismissi…

We re-uploaded Gemma4 4 times - 3 times were due to 20 llama.cpp bug fixes, which we helped solve some as well. The 4th is an official Gemma chat template improvement from Google themselves, so these are out of our hands. All providers had to re-fix their uploads, so not just us. For MiniMax 2.7 - there were NaNs, but it wasn't just ours - all quant providers had it - we identified 38% of bartowski's had NaNs. Ours w…

Just curious, the fixes are not about weights but about templates, am I right?

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

#416

Post by throwdbaaway »

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.

Based on the release schedule of 3.5 previously, my optimistic take is that they distill the small models from the 397B, and it is much faster to distill a sparse A3B model. Hopefully the other variants will be released in the coming days.

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

#417

Post by seemaze »

3836293648 wrote: post #377
jwitthuhn wrote: post #297

Earlier quoted context omitted.

I've been largely using Qwen3.5-122b at 6 bit quant locally for some c++/go/python dev lately because it is quite capable as long as I can give it pretty specific asks within the codebase and it will produce code that needs minimal massaging to fit into the project. I do have a $20 claude sub I can fall back to for anything qwen struggles with, but with 3.5 I have been very pleased with the results.

How much VRAM do you need for that?

I squeeze Qwen3.5-122B-A10B at Q6 into 128GB. It's a great model.

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

#419

Post by bigiain »

bdangubic wrote: post #359
hparadiz wrote: post #352

Earlier quoted context omitted.

There are way too many good uses of these models for local that I fully expect a standard workstation 10 years from now to start at 128GB of RAM and have at least a workstation inference device.

or if you believe a lot of HN crowd we are in AI bubble and in 10 years inference will be dirt cheap when all of this crashes and we have all this hardware in data centers and it won't make any sense to run monster workstations at home (I work 128GB M4 but not run inference, just too many electron apps running at the same time...) :)

> I work 128GB M4 but not run inference, just too many electron apps running at the same time.

This is somewhat depressing - needing a couple of thousand bucks worth of ram just to run your chat app and code/text editor and API doco tool and forum app and notetaking app all at the same time...

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

#420

Post by zackify »

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?

always inside claude code, just using ollama, takes 2 seconds
Post reply on HN