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

231–240 of 482 posts

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

#231

Post by czk »

Oras wrote: post #98
Aurornis wrote: post #23

Earlier quoted context omitted.

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…

If these models reach quality of Opus 4.5, then DGX could be a good alternative for serious dev teams to run local models. It is not that expensive and has short time to make ROI

Memory bandwidth is the biggest L on the dgx spark, it’s half my MacBook from 2023 and that’s the biggest tok/sec bottleneck

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

#232

Post by interstice »

refulgentis wrote: post #200
simonw wrote: post #186

Earlier quoted context omitted.

There's a bunch of useful information in my comment that's independent of the fact that it drew a pelican: 1. You can run this on a Mac using llama-server and a 17GB downloaded file 2. That version does indeed produce output (for one specific task) that's of a good enough quality to be worth spending more time checking out this model 3. It generated 4,444 tokens in 2min 53s, which is 25.57 tokens/s

Right, that is exactly what I meant by "the root post [had info about Qwen]" - you shouldn't feel I'm being critical of you or asking you to do anything different, at all. I admire you deeply and feel humbled* by interacting with you, so I really want that to be 100% clear, because this is the 2nd time I'm reading that it might be personal. * er, that probably sounds strange, but I did just spend 6 weeks working on i…

Somewhat ironically - as of when I write this this tangent is dominating the size of this topic.

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

#233

Post by mlyle »

refulgentis wrote: post #200
simonw wrote: post #186

Earlier quoted context omitted.

There's a bunch of useful information in my comment that's independent of the fact that it drew a pelican: 1. You can run this on a Mac using llama-server and a 17GB downloaded file 2. That version does indeed produce output (for one specific task) that's of a good enough quality to be worth spending more time checking out this model 3. It generated 4,444 tokens in 2min 53s, which is 25.57 tokens/s

Right, that is exactly what I meant by "the root post [had info about Qwen]" - you shouldn't feel I'm being critical of you or asking you to do anything different, at all. I admire you deeply and feel humbled* by interacting with you, so I really want that to be 100% clear, because this is the 2nd time I'm reading that it might be personal. * er, that probably sounds strange, but I did just spend 6 weeks working on i…

I like the pelican-bicycle test because it's pretty predictive of how the model does helping me with TikZ. And I hate writing TikZ.

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

#234

Post by ozgrakkurt »

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…

I just assume any of those companies would steal my work and wouldn't care about it.

Everything they have done so far indicates this.

Running your own is the only option unless you really trust them or unless you have the option to sue them like some big companies can.

Or if you don't really care then you can use the chineese one since it is cheaper.

What makes you trust Anthropic more than Alibaba?

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

#236

Post by anonym29 »

hedgehog wrote: post #92
muyuu wrote: post #62

Earlier quoted context omitted.

i have a Strix Halo machine typically those dense models are too slow on Strix Halo to be practical, expect 5-7 tps you can get an idea by looking at other dense benchmarks here: https://strixhalo.zurkowski.net/experiments - i'd expect this model to be tested here soon, i don't think i will personally bother

This one is around 250 t/s prefill and 12.4 generation in my testing.

similar numbers here - slightly higher PP. slightly better peak speed and retention w/ q8_0 kv cache quants too. llama-bench results here, cba to format for hn: https://pastebin.com/raw/zgJeqRbv

GTR 9 Pro, "performance" profile in BIOS, GTT instead of GART, Fedora 44

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

#237

Post by SlavikCA »

maxloh wrote: post #230
SlavikCA wrote: post #227

Earlier quoted context omitted.

I'm getting 30 t/s on RTX 4090D (using 42 out of 48GB VRAM) with UD-Q6_K_XL https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/discussions/...

I thought Q4_K_M is the standard. Why did you choose the 6-bit variant? Does it generate better input?

There is no standard.

The higher quantization - the better results, but more memory is needed. Q8 is the best.

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

#238

Post by j-bos »

otabdeveloper4 wrote: post #125
fnordpiglet wrote: post #84

Earlier quoted context omitted.

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…

> For coding often quality at the margin is crucial even at a premium. For coding, quality is not measurable and is based entirely on feels (er, sorry, "vibes"). Employers paying for SOTA models is nothing but a lifestyle status perk for employees, like ping-pong tables or fancy lunch snacks.

"based entirely on feels"

Now there's a word I haven't heard in a long, long time.

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

#239

Post by echelon »

simonw wrote: post #106

The pelican is excellent for a 16.8GB quantized local model: https://simonwillison.net/2026/Apr/22/qwen36-27b/ I ran it on an M5 Pro with 128GB of RAM, but it only needs ~20GB of that. I expect it will run OK on a 32GB machine. Performance numbers: Reading: 20 tokens, 0.4s, 54.32 tokens/s Generation: 4,444 tokens, 2min 53s, 25.57 tokens/s I like it better than the pelican I got from Opus 4.7 the other day: https://si…

Metrics and toy examples can be gamed. Rather than these silly examples, how does it feel?

Can you replace Claude Code Opus or Codex with this?

Does it feel >80% as good on "real world" tasks you do on a day to day basis.

Post reply on HN