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

101–110 of 482 posts

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

#101

Post by wuschel »

danielhanchen wrote: post #73
ryandrake wrote: post #67

Earlier quoted context omitted.

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…

We made Unsloth Studio which should help :) 1. Auto best official parameters set for all models 2. Auto determines the largest quant that can fit on your PC / Mac etc 3. Auto determines max context length 4. Auto heals tool calls, provides python & bash + web search :)

Great project! Thank you for that!

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

#102

Post by mchusma »

Aurornis wrote: post #75
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

I use Opus and the Qwen models. The gap between them is much larger than the benchmark charts show. If you want to compare to a hosted model, look toward the GLM hosted model. It’s closest to the big players right now. They were selling it at very low prices but have started raising the price recently.

I like both GLM and Kimmi 2.6 but honestly for me they didn’t have quite the cost advantage that I would like partly because they use more tokens so they end up being maybe sonnet level intelligence at haiku level cost. Good but not quite as extreme as some people would make them out to be and for my use cases running the much cheaper, Gemma 4 four things where I don’t need Max intelligence and running sonnet or opus for things where I need the intelligence and I can’t really make the trade-off is been generally good and it just doesn’t seem worth it to cost cut a little bit. Plus when you combine prompt, cashing and sub agents using Gemma 4, the cost to run sonnet or even opus, are not that extreme.

For coding $200 month plan is such a good value from anthropic it’s not even worth considering anything else except for up time issues

But competition is great. I hope to see Anthropic put out a competitor in the 1/3 to 1/5 of haiku pricing range and bump haiku’s performance should be closer to sonnet level and close the gap here.

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

#103

Post by wuschel »

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…

> but the quality of output will not be usable

Making the the right pick for model is one of the key problems as a local user. Do you have any references where one can see a mapping of problem query to model response quality?

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

#105

Post by ryandrake »

Aurornis wrote: post #80
ryandrake wrote: post #67

Earlier quoted context omitted.

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…

> 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 problem, but which one do you choose? Unsloth offers[1] four of them: UD-IQ3_XXS, Q3_K_S, Q3_K_M, UD-Q3_K_XL There are actually two problems with this: First, the 3-bit quants are where the quality loss really becomes obvious. You can get it to run, but you’re not getting the quality you expected. The e…

Yea, I'm also kind of jealous of Apple folks with their unified RAM. On a traditional homelab setup with gobs of system RAM and a GPU with relatively little VRAM, all that system RAM sits there useless for running LLMs.

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

#106

Post by simonw »

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://simonwillison.net/2026/Apr/16/qwen-beats-opus/

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

#107

Post by bityard »

rubiquity wrote: post #56
amunozo wrote: post #2

A bit skeptical about a 27B model comparable to opus...

You should try it out. I'm incredibly impressed with Qwen 3.5 27B for systems programming work. I use Opus and Sonnet at work and Qwen 3.x at home for fun and barely notice a difference given that systems programming work needs careful guidance for any model currently. I don't try to one shot landing pages or whatever.

Are you using the same agent/harness/whatever for both Claude and Qwen, or something different for each one?

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

#108

Post by throwaw12 »

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…

I feel like this time it is indeed in the training set, because it is too good to be true.

Can you run your other tests and see the difference?

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

#109

Post by kpw94 »

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…

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)

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

#110

Post by zozbot234 »

ryandrake wrote: post #105
Aurornis wrote: post #80

Earlier quoted context omitted.

> 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 problem, but which one do you choose? Unsloth offers[1] four of them: UD-IQ3_XXS, Q3_K_S, Q3_K_M, UD-Q3_K_XL There are actually two problems with this: First, the 3-bit quants are where the quality loss really becomes obvious. You can get it to run, but you’re not getting the quality you expected. The e…

Yea, I'm also kind of jealous of Apple folks with their unified RAM. On a traditional homelab setup with gobs of system RAM and a GPU with relatively little VRAM, all that system RAM sits there useless for running LLMs.

That "traditional" setup is the recommended setup for running large MoE models, leaving shared routing layers on the GPU to the extent feasible. You can even go larger-than-system-RAM via mmap, though at a non-trivial cost in throughput.
Post reply on HN