Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

qwen.ai

Post reply on HN
Print view View original

211–220 of 482 posts

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#211

Post by varispeed »

Aurornis wrote: post #23
anonzzzies wrote: post #11

I wish that all announcements of models would show what (consumer) hardware you can run this on today, costs and tok/s.

The 27B model they release directly would require significant hardware to run natively at 16-bit: A Mac or Strix Halo 128GB system, multiple high memory consumer GPUs, or an RTX 6000 workstation card. This is why they don’t advertise which consumer hardware it can run on: Their direct release that delivers these results cannot fit on your average consumer system. Most consumers don’t run the model they release direct…

Is it the same idea that when you go to luxury store you don't see prices on display?

Seems like nobody wants to admit they exclude working class from the ride.

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#212

Post by rmacqueen »

fnordpiglet wrote: post #84
jameson wrote: post #74

What competitive advantage does OpenAI/Anthropic has when companies like Qwen/Minimax/etc are open sourcing models that shows similar (yet below than OpenAI/Anthropic) benchmark results? Also, the token prices of these open source models are at a fraction of Anthropic's Opus 4.6[1] [1]: https://artificialanalysis.ai/models/#pricing

For coding often quality at the margin is crucial even at a premium. It’s not the same as cranking out spam emails or HN posts at scale. This is why the marginal difference between your median engineer and your P99 engineer is comp is substantial, while the marginal comp difference between your median pick and packer vs your P99 pick and packer isn’t. I’d also say it keeps the frontier shops competitive while costing…

> This is why the marginal difference between your median engineer and your P99 engineer is comp is substantial, while the marginal comp difference between your median pick and packer vs your P99 pick and packer isn’t.

That's an interesting analogy.

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#213

Post by skiing_crawling »

vladgur wrote: post #12

This is getting very close to fit a single 3090 with 24gb VRAM :)

I used to run qwen3.5 27b Q4_k_M on a single 3090 with these llama-server flags successfully: `-ngl 99 -c 262144 -fa on --cache-type-k q4_0 --cache-type-v q4_0`

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#215

Post by verdverm »

danielhanchen wrote: post #53
verdverm wrote: post #21

Earlier quoted context omitted.

That was quick (compared to the 1T Kimi-2.6, not surprising)

Haha :) We had some issues with Kimi-2.6 since it was int4 and we were investigating how to handle it :)

Appreciate what y'all do! We were slacking about how many HGX-B300 it would take to run Kimi and it looks like we could actually fit 2-3 Kimis on a single HGX.

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#217

Post by green7ea »

doix wrote: post #68
vibe42 wrote: post #65

Q4-Q5 quants of this model runs well on gaming laptops with 24GB VRAM and 64GB RAM. Can get one of those for around $3,500. Interesting pros/cons vs the new Macbook Pros depending on your prefs. And Linux runs better than ever on such machines.

What laptop has that much VRAM and RAM for $3500 with good/okay-ish Linux support? I was looking to upgrade my asus zephyrus g14 from 2021 and things were looking very expensive. Decided to just keep it chugging along for another year. Then again, I was looking in the UK, maybe prices are extra inflated there.

I got a HP g1a for about 3k€ with 64gb of ram when it came out

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#218

Post by ai_critic »

simonw wrote: post #195
rob wrote: post #177

Earlier quoted context omitted.

I think it's to help drive traffic to his blog now that he's accepted sponsors in the header of every page. I do see this pelican thing come up from him on every model post that gets released.

The traffic I get from a comment with a link to a pelican is pretty tiny.

"Create me an SVG to drive MAXIMUM ENGAGEMENT for my sponsors".

Missing an opportunity here, lol.

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#219

Post by zargon »

bityard wrote: post #76
anonzzzies wrote: post #11

I wish that all announcements of models would show what (consumer) hardware you can run this on today, costs and tok/s.

There are infinite combinations of CPU/GPU capable of running LLMs locally. What most people do is buy the system they can afford and roughly meets their goals and then ball-park VRAM usage by looking at the model size and quantization. For more a detailed analysis, there are several online VRAM calculators. Here's one: https://smcleod.net/vram-estimator/ If you have a huggingface account, you can set your system con…

These calculators are almost entirely useless. They don't understand specific model architectures. Even the ones that try to support only specific models (like the apxml one) get it very wrong a lot of the time.

For example, the one you linked, when I provide a Qwen3.5 27B Q_4_M GGUF [0], says that it will require 338 GB of memory with 16-bit kv cache. That is wrong by over an order of magnitude.

[0] https://huggingface.co/bartowski/Qwen_Qwen3.5-27B-GGUF/resol...

Re: Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

#220

Post by Someone1234 »

syntaxing wrote: post #104

Been using Qwen 3.6 35B and Gemma 4 26B on my M4 MBP, and while it’s no Opus, it does 95% of what I need which is already crazy since everything runs fully local.

You've got me curious. Two questions if I may:

- What kind of tasks/work?

- How is either Qwen/Gemma wired up (e.g. which harness/how are they accessed)?

Or to phase another way; what does your workflow/software stack look like?

Post reply on HN