Qwen 3.6 27B is the sweet spot for local development • Hacker News Board

Re: Qwen 3.6 27B is the sweet spot for local development

#81

Post by ddalex » Mon, Jun 29, 2026, 6:11 PM UTC

dofm wrote: post #50

bensyverson wrote: post #26

The article is based on running Qwen 3.6 on a 128GB MacBook Pro. For reference, a 128GB MBP currently starts at $6699 USD [0] Some people will be happy to pay that premium for privacy, but at roughly 10X the cost of a MacBook Neo, that money could also buy a lot of credits on OpenRouter or frontier labs. [0]: https://www.apple.com/shop/buy-mac/macbook-pro/14-inch-space...

The maths there is pretty undeniable, but it is not where I'd make the split. Having a machine that can run some modest local LLMs, like the Gemma 4 12B, is really worth it. I don't know how much serious hands-free agentic coding I will ever do on my MacBook alone, but I do know that I would not have got so far into understanding this without tinkering with local models, llama.cpp, LM Studio, and LM Studio and all th…

I just got Claude to download and install all the models and servers and agents and prepare all the launch scripts for me... no need to learn, just ask it to do it for you

Re: Qwen 3.6 27B is the sweet spot for local development

#82

Post by DanHulton » Mon, Jun 29, 2026, 6:13 PM UTC

kllrnohj wrote: post #34

0x0000000 wrote: post #19

> ... on my Macbook Max M5 128 GB Local development for who ? How many of y'all are rocking 128GB of memory? Am I reading Apple's site correctly that it's a $10,000 laptop?

You don't need nearly that much RAM to run Qwen 3.6 27B, though. qwen3.6:27b-q4_K_M is only 17GB, for example.

This is what I run on an M5 MacBook Air 32GB. Works great.

I’m not having it build whole features from scratch, though. I give it pretty explicit instructions closer to the class or function level, and it still saves me an immense amount of time, while I’m very connected to the code that’s written.

Definitely the sweet spot for me.

Re: Qwen 3.6 27B is the sweet spot for local development

#83

Post by doodlesdev » Mon, Jun 29, 2026, 6:13 PM UTC

I feel like I'm going insane seeing people buy these 128gb MBP for thousands of dollars to run models that are objectively much worse than SOTA and spending so much more. The amount spent on a 128gb M5 MAX can buy you a damned new car here. What the hell am I missing? Are developers in other countries living in such different worlds?

(I'm aware the price is, in absolute terms, more expensive where I live compared to the USA. That reinforces what I think, because anyone sane that would've bought one of those in another country would sell them as soon as they landed here and save that money.)

Re: Qwen 3.6 27B is the sweet spot for local development

#84

Post by jjcm » Mon, Jun 29, 2026, 6:13 PM UTC

I'd also look at the qwopus distil if you're using qwen 3.6 27b. It's a nice refinement of the current 27b with slightly better stats.

Jackrong has a few different ones available depending on what you're trying to do: https://huggingface.co/Jackrong

Re: Qwen 3.6 27B is the sweet spot for local development

#85

Post by BoredomIsFun » Mon, Jun 29, 2026, 6:14 PM UTC

anonym29 wrote: post #22

Strix Halo user here. While Qwen 3.6 27B exhibits remarkable intelligence density, I will still take unsloth's dynamic IQ2_XXS of Minimax M2.7 over Q8_0 Qwen 3.6 27B any day of the week, and this isn't just because of generation speed either. I wrote my own custom harness, and I get hallucinated tool call parameters and bizarre invocations with Q3.6 27B even at Q8_0, but no issues with the IQ2_XXS of M2.7.

> I get hallucinated tool call parameters and bizarre invocations

tweaking sampler might help

Re: Qwen 3.6 27B is the sweet spot for local development

#86

Post by markdog12 » Mon, Jun 29, 2026, 6:14 PM UTC

I've tested it extensively for actual local development for my job, and hard disagree here. It's a waste of time to use it. Wish it were not true.

Re: Qwen 3.6 27B is the sweet spot for local development

#87

Post by CurbStomper » Mon, Jun 29, 2026, 6:14 PM UTC

[dead]

Re: Qwen 3.6 27B is the sweet spot for local development

#88

Post by SkitterKherpi » Mon, Jun 29, 2026, 6:15 PM UTC

27-30B in general seems to be the level where you actually start having decent models. I just wish consumer hardware hadn't stagnated so much that we can't easily go higher than that, and that even running those requires a $5k machine now.

Re: Qwen 3.6 27B is the sweet spot for local development

#89

Post by dmezzetti » Mon, Jun 29, 2026, 6:15 PM UTC

Local models are great for a lot of things past just software development. We need to move towards solving other real world problems vs just building software. I've been focused on that with TxtAI (https://github.com/neuml/txtai) for 6 years now.

Re: Qwen 3.6 27B is the sweet spot for local development

#90

Post by iwontberude » Mon, Jun 29, 2026, 6:16 PM UTC

blopker wrote: post #80

I've been working with local models for the past year. There's so many possibilities, but I don't think coding is one. Coding requires so many layers beyond inference; I spent so much time trying to replicate what Claude Code does end to end locally. Understanding all the layers and keeping up with the advancements feels like a slog. Even this article messes up and misunderstands what some of the settings are doing.…

> I don't think coding is one

Certainly this is falsifiable easily by any of us doing it on a regular basis

> Qwen stuck in thought loops

This does happen when context is not managed effectively; creating plans, using subagents and compactions strategically resolves this