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

141–150 of 482 posts

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

#141

Post by refulgentis »

Marciplan wrote: post #93
yrds96 wrote: post #87

Earlier quoted context omitted.

I wonder if this became a so well known "benchmark" that models already got trained for it.

every model release Simon comes with his Pelican and then this comment follows. Can we stop both? its so boring

I really appreciate you speaking up. Happened yesterday on GPT Image 2, bit my tongue b/c people would see it as fun policing, and same thing today. And it happens on every. single. LLM. release. thread.

It's disruptive to the commons, doesn't add anything to knowledge of a model at this point, and it's way out of hand when people are not only engaging with the original and creating screenfuls to wade through before on-topic content, but now people are creating the thread before it exists to pattern-match on the engagement they see for the real thing. So now we have 2x.

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

#143

Post by syntaxing »

throwaw12 wrote: post #135
syntaxing wrote: post #132

Earlier quoted context omitted.

1. What do you mean by accuracy? Like the facts and information? If so, I use a Wikipedia/kiwx MCP server. Or do you mean tool call accuracy? 2. 3.6 is noticeably better than 3.5 for agentic uses (I have yet to use the dense model). The downside is that there’s so little personality, you’ll find more entertainment talking to a wall. Anything for creative use like writing or talking, I use Gemma 4. I also use Gemma 4…

by accuracy I meant how close is the output to your expectations, for example if you ask 8B model to write C compiler in C, it outputs theory of how to write compiler and writes pseudocode in Python. Which is off by 2 measures: (1) I haven't asked for theory (2) I haven't asked to write it in Python. Or if you want to put it differently, if your prompt is super clear about the actions you want it to do, is it followi…

Ironically, even though I write C/++ for a living, I don’t use it for personal projects so I can’t say how well it works for low level coding. Python works great but there’s a limit on context size (I just don’t have enough RAM, and I do not like quantizing my kv cache). Realistically, I can fit 128K max but I aim for 65K before compacting. With Unsloth’s Opencode templating, I haven’t had any major issues but I haven’t done anything intense with it as of late. But overall, I have not had to stop it from an endless loop which happened often on 3.5.

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

#144

Post by zargon »

kpw94 wrote: post #109
benob wrote: post #27

Earlier quoted context omitted.

I get ~5 tokens/s on an M4 with 32G of RAM, using: llama-server \ -hf unsloth/Qwen3.6-27B-GGUF:Q4_K_M \ --no-mmproj \ --fit on \ -np 1 \ -c 65536 \ --cache-ram 4096 -ctxcp 2 \ --jinja \ --temp 0.6 \ --top-p 0.95 \ --top-k 20 \ --min-p 0.0 \ --presence-penalty 0.0 \ --repeat-penalty 1.0 \ --reasoning on \ --chat-template-kwargs '{"preserve_thinking": true}' 35B-A3B model is at ~25 t/s. For comparison, on an A100 (~RTX…

When you say tok/s here are you describing the prefill (prompt eval) token/s or the output generation tok/s? (Btw I believe the "--jinja" flag is by default true since sometime late 2025, so not needed anymore)

If someone doesn't specifically say prefill then they always mean decode speed. I have never seen an exception. Most people just ignore prefill.

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

#145

Post by taspeotis »

simonw wrote: post #138
refulgentis wrote: post #137

Earlier quoted context omitted.

Hoping this doesn't turn into a pelican-SVG back-and-forth: yesterday's GPT Image 2 thread ended up being three screenfuls of "I tried the prompt too" replies, and nothing on the model until you scroll past it. I appreciate the testing, and I know this sounds like fun police, but there's a pattern where well-known commenter + one-off vibe test + 1:1 sub-threads eats the whole discussion. It being fun makes it hard to…

You can collapse the pelican thread with the little [-] toggle at the top.

Why would you though?

And by the way: Thanks for relentlessly holding new models’ feet to the pelican SVG fire.

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

#146

Post by esskay »

random3 wrote: post #71
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.

Check out https://www.canirun.ai/ (and https://news.ycombinator.com/item?id=47363754 )

CaniRun's not a great tool - look how long its been since it's been updated. It's not got any of the qwen3.6 models on the list nor the new kimi one. In fact it's missing many of the "popular" models.

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

#147

Post by fnordpiglet »

bigbadfeline wrote: post #131
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 That's a cryptic way to say "Only for vibe-coding quality at the margin matters". Obviously, quality is determined first and foremost by the skills of the human operating the LLM. > No one really believes at face value a Chinese hosted firm isn’t mass trolling every competitive advantage possible That's much easier to believe than the same but appl…

1) model provider choices don’t obviate the need to make other good choices

2) I think there is a special case for Chinese providers due to the philosophical differences in what constitutes fair markets and the regulatory and civil legal structure outside China generally makes such things existentially dangerous to do; hence while it might happen it is extraordinarily ill advised, while in China is implicitly the way things work. However my point is Ali has their own hosted version of Qwen models operating on the frontier that are at minimum hosted exclusively before released. Theres no reason to believe they won’t at some point exclusively host some frontier or fine tuned variants for purposes for commercial reasons. This is part of why they had recent turnover.

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

#148

Post by cbg0 »

otabdeveloper4 wrote: post #129
cbg0 wrote: post #72

Earlier quoted context omitted.

If all you're looking at is benchmarks that might be true, but those are way too easy to game. Try using this model alongside Opus for some work in Rust/C++ and it'll be night and day. You really can't compare a model that's got trillions of parameters to a 27B one.

> ...and it'll be night and day. That's just, like, your opinion, man. > You really can't compare a model that's got trillions of parameters to a 27B one. Parameter count doesn't matter much when coding. You don't need in-depth general knowledge or multilingual support in a coding model.

I often do need in-depth general knowledge in my coding model so that I don't have to explain domain specific logic to it every time and so that it can have some sense of good UX.

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

#149

Post by fnordpiglet »

rohansood15 wrote: post #91
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…

Most code is not P99 though. Also, have you considered that your trust in Anthropic and distrust in China may not be shared by many outside the US? There's a reason why Huawei is the largest supplier of 5G hardware globally.

I find it hard to believe anyone who has ever done business inside China doesn’t know that the structure of Chinese business is built around massive IP theft and repurposing on a state wide systematic level. It’s not a nationalism point, it’s an objective and easily verified truth.

Most code is not P99, but companies pay a premium to produce code that is. That’s my point.

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

#150

Post by wuschel »

benob wrote: post #27
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.

I get ~5 tokens/s on an M4 with 32G of RAM, using: llama-server \ -hf unsloth/Qwen3.6-27B-GGUF:Q4_K_M \ --no-mmproj \ --fit on \ -np 1 \ -c 65536 \ --cache-ram 4096 -ctxcp 2 \ --jinja \ --temp 0.6 \ --top-p 0.95 \ --top-k 20 \ --min-p 0.0 \ --presence-penalty 0.0 \ --repeat-penalty 1.0 \ --reasoning on \ --chat-template-kwargs '{"preserve_thinking": true}' 35B-A3B model is at ~25 t/s. For comparison, on an A100 (~RTX…

How is the quality of model answers to your queries? Are they stable over time?

I am wondering how to measure that anyway.

Post reply on HN