Live data from Hacker News

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

qwen.ai

421–430 of 482 posts

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

#421

Earlier quoted context omitted.

1. Qwen is mostly coding related through Opencode. I have been thinking about using pi agent and see if that works better for general use case. The usefulness of *claw has been limited for me. Gemma is through the chat interface with lmstudio. I use it for pretty much everything general purpose. Help me correct my grammar, read documents (lmstudio has a built in RAG tool), and vision capabilities (mentioned below, jo…

Curious how do you run opencode and qwen locally? Few times I tried it responds back with some nonsense. Chat, say, through ollama works well.

Which quants are you using? I had similar issue until I used Unsloth’s. I would recommend at least UD_6. Also, make sure your context length is above 65K.

https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF

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

#422
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…

it seemed HN was moving the right direction when we added the "no AI comments", and yet, every single post about a new model is from you and your pelican. it's tired. please stop, it adds no value and has become cliche.

I think it added plenty of value!

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

#424
post #303

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.

I use Qwen 3.5 122B on an RTX PRO 6000 with open code, and very pleased. I don't feel a need for using a closed model any more. The result after answering questions in Plan mode is almost always what I want, with very few occasional bugs. It does a lot of effort to see how the code I am working on is written now while extending it in the same style.

If they release a Qwen 3.6 that also makes good use of the card, may move to it.

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

#425
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…

IMHO looks more like a stork, not a pelican. Look up any image of an actual pelican and check the ratio of legs to body. IMHO that's a weird mistake to make when asked for a "pelican".

Have you considered asking a couple of artists on Fiverr or something to draw you a picture with the same prompt? I don't mean this as a gotcha, it's actual advice, you should probably get a sense of what a real human artist/designer (or three) would do with this prompt.

For example, I hope you will find that: One reasoning choice is wrong with this picture that's not much to do with its ability to draw. Do we enlarge the pelican to human size? Or do we shrink the bike to pelican size? There is only one answer that keeps pelican proportions. Draw a pelican on a very tiny bike, and its legs will just fit without making it a different species, and you can even sort of cover part of the steer under the wings, etc etc.

I'm curious if other artists would come up with the same or other solutions, but they should in general come up with solutions, which I haven't seen the LLM do, really.

You (or maybe others?) said that the "pelican on a bike" prompt is good because "there is no right answer" cause you can't really fit a pelican on a bike. But most artists will say "hold my beer" and figure it out anyway. Cartoonists won't even have to think. The "figuring out" of these problems is what I'm missing in the LLMs response. It just put a pelican on a bike and makes it look like a stork if necessary. I don't really feel like it's actually testing for the thing this prompt is designed for, unless the test still says "FAIL" for each and all of them, including the one you just called "excellent".

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

#426
post #162
post #153

Earlier quoted context omitted.

if they cook these in, i wonder what else was cooked in there to make it look good.

Everything is benchmaxxed. Whack-a-mole training is at least as representative of what is getting added to models as more general training advances.

[dead]

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

#427

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…

I can run Qwen3.5-27B-Q4_K_M on my weird PC with 32 GB of system memory and 6 GB of VRAM. It's just a bit slow, is all. I get around 1.7 tokens per second. IMO, everyone in this space is too impatient. (Intel Core i7 4790K @ 4 Ghz, nVidia GTX Titan Black, 32 GB 2400 MHz DDR3 memory) Edit: Just tested the new Qwen3.6-27B-Q5_K_M. Got 1.4 tokens per second on "Create an SVG of a pellican riding a bicycle." https://gist.…

I have been using Qwen3.5-9B-UD-Q4_K_XL.gguf on an 8GB 3070Ti with llama.cpp server and I get 50-60 tok/s.

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

#428
post #335

Earlier quoted context omitted.

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

That post doesn't say anything about training for SVG generation

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

#429

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…

Tbf the Sparks usefulness isn’t for inference IMO. Its memory bandwidth is too low for that.

But on the other hand, running Qwen 3.5 122B A10B locally on it using ~110GB of memory and getting 50tk/s generation and quite excellent prefill… I couldn’t do that on many other machines at this price point

For me this has been awesome to learn CUDA on, fine tuning models (until I get it close to what I want then it’s off to H100 or something clusters) and a bit of inference on the side

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

#430
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…

IMHO looks more like a stork, not a pelican. Look up any image of an actual pelican and check the ratio of legs to body. IMHO that's a weird mistake to make when asked for a "pelican". Have you considered asking a couple of artists on Fiverr or something to draw you a picture with the same prompt? I don't mean this as a gotcha, it's actual advice, you should probably get a sense of what a real human artist/designer (…

Honestly it never crossed my mind to waste some artist's time with this, but now that the joke "benchmark" has somehow reached orbital velocity maybe I should be thinking about it!

I've run the prompt through dozens of dedicated image generation models so I've seen many versions of this that are better attempts than a text model spitting out SVG - here's gpt-image-2 as a recent example: https://chatgpt.com/share/69ea21ab-8738-83e8-a4d7-67374d84e0...

Post reply on HN