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

331–340 of 482 posts

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

#331

Post by verdverm »

chr15m wrote: post #303
datadrivenangel wrote: post #280

Earlier quoted context omitted.

Gemma4 feels the most "claude-like" of all the models I've run locally on my M5 mbp.

I found on coding tasks that Qwen 3.5 can actually do the thing whereas Gemma 4 went off the rails frequently. Will try this new 3.6 release today.

There was a qwen-3.6 MoE six days ago that I thought was better than Gemma 4. Today's is a dense model. (gemma release both a 26B MoE and a 31B dense at the same time)

I have intention to evaluate all four on some evals I have, as long as I don't get squirrelled again.

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

#332

Post by qudat »

domh wrote: post #228
docheinestages wrote: post #222

Has anyone tried using this with a Claude Code or Qwen Code? They both require very large context windows (32k and 16k respectively), which on a Mac M4 48GB serving the model via LM Studio is painfully slow.

I had the best success yet earlier today running https://pi.dev with a local gemma4 model on ollama on my m4 Mac with 48GB ram. I think pi is a lot lighter than Claude code.

I didn’t think pi supported local models?

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

#334

Post by verdverm »

donmcronald wrote: post #63
originalvichy wrote: post #19

Earlier quoted context omitted.

Yup! Smaller quants will fit within 24GB but they might sacrifice context length. I’m excited to try out the MLX version to see if 32GB of memory from a Pro M-series Mac can get some acceptable tok/s with longer context. HuggingFace has uploaded some MLX versions already.

I have an Mini M4 Pro with 64GB of 273GB/s memory bandwidth and it's borderline with 3.5-27B. I assume this one is the same. I don't know a ton, but I think it's the memory bandwidth that limits it. It's similar on a DGX Spark I have access to (almost the same memory bandwidth). It's been a while since I tried it, but I think I was getting around 12-15 tokens per second an that feels slow when you're used to the big…

There are a number of DGX benchmarks for these recent gemma-4 / qwen-3.6 models on the nvidia forum, ex: https://forums.developer.nvidia.com/t/qwen-qwen3-6-35b-a3b-a...

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

#335

Post by simonw »

mudkipdev wrote: post #285
simonw wrote: post #187

Earlier quoted context omitted.

See https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

Why is the assumption that they trained for a pelican on a bicycle, rather than running RL for all kinds of 'generate an SVG' tasks?

Gemini did exactly that, and boasted about it at launch: https://x.com/JeffDean/status/2024525132266688757

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

#337

Post by dannyw »

ryandrake wrote: post #67
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…

Yea, this is currently the confusing part of running local models for newbies: Even after you have decided which model you want to run, and which org's quantizations to use (let's just assume Unsloth's for example), there are often dozens of quantizations offered, and choosing among them is confusing. Say you have a GPU with 20GB of VRAM. You're probably going to be able to run all the 3-bit quantizations with no pro…

Evaluating different quant levels for your use case is a problem you can pretty reliably throw at a coding agent and leave overnight though. At least, it should give you a much smaller shortlist.

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

#338

Post by angoragoats »

overgard wrote: post #310
pawelduda wrote: post #297

Earlier quoted context omitted.

How many tokens/s do you get on RTX 5090?

Can't answer for an RTX 5090, but for an RTX 5080 16GB of RAM (desktop), I get about 6 tokens/sec after some tweaking (f16->q4_0). Kind of on the borderline of usable.. probably realistically need either a 5090 with more RAM or something like a Mac with a unified memory architecture.

A Mac is not going to be all that much faster than a 5080 with any models, other than the ones you can’t currently run at all because you don’t have enough GPU+CPU memory combined.

You’re much better off adding a second GPU if you’ve already got a PC you’re using.

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

#339

Post by __s »

djyde wrote: post #311
finnjohnsen2 wrote: post #261

Since Gemma 4 came this easter the gap from self hosting models to Claude has decreased sigificantly I think. The gap is still huge it just that local models were extremely non-competitive before easter. So now it seems Qwen 3.6 is another bump up from Gemma 4 which is exciting if it is so. I keep an Opus close ofcourse, because these local models still wander off in the wrong direction and fails. Something Opus almo…

What level of programming tasks can a 27B model handle? Even with Claude, I'm occasionally not satisfied, and I can't imagine how effective a 27B model would be.

Basic triage is good. I've found I need to mostly handle programming, but local models have been good for pointing me at where to look with just "investigate https://github.com/HarbourMasters/Shipwright/issues/6232" as prompt
Post reply on HN