Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen 3.6 27B is the sweet spot for local development

quesma.com

Post reply on HN
Print view View original

451–460 of 809 posts

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

#451

Post by bilekas »

iagooar wrote: post #199

I love my MacBook Pro M5 128GB RAM and I love qwen3.6. BUT DO NOT buy this MacBook if you plan on doing serious coding using local LLMs with it. The reason is simple: your fingers will burn and your head will explode from the noise. Running any kind of sophisticated job on the very laptop you are using is just not viable. Sure you can use it in clamshell mode, but forget touching it while working with AI coding or ag…

Can you define "serious programming"? Because I use it to implement things I COULD go and figure out like algorithms or test generation or evaluations etc, the "serious" programming I tend to do myself. That is what I'm paid for.

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

#452

Post by freehorse »

kristianp wrote: post #331
iagooar wrote: post #290

Earlier quoted context omitted.

M5 Max. But I also have a MacMini M4 Pro 64GB. Qwen3.6 runs on the M4 just fine - sure the M5 is at least 2x the speed. If Apple launches a MacMini with an M5, I will be the 1st one to get it.

You're only going to get an incremental improvement with an M5 Pro mini compared to an M4 Pro mini. Memory bandwidth goes from 273GB/s to 307GB/s, about 12.5% improvement for LLMs.

M5's have the neural accelarator that boosts prefill speed a lot. But token generation itself will not change that much, that's true.

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

#453

Post by inventor7777 »

jarjoura wrote: post #287
iagooar wrote: post #199

I love my MacBook Pro M5 128GB RAM and I love qwen3.6. BUT DO NOT buy this MacBook if you plan on doing serious coding using local LLMs with it. The reason is simple: your fingers will burn and your head will explode from the noise. Running any kind of sophisticated job on the very laptop you are using is just not viable. Sure you can use it in clamshell mode, but forget touching it while working with AI coding or ag…

TBF, I just recently picked up this same model, and it's reminding me of the last gen Intel i9 MBP. Just visiting any non-basic website spins up the fans and battery life isn't great either. Yes, this thing is fast, but damn it gets hot just using it for normal tasks. Still, I don't agree. I think this machine is meant to use local models. You just have to wear pants if you want to keep it directly on your lap. I rar…

That seems very unusual for modern Apple Silicon. Our family has:

- M3 Pro MacBook Pro 36GB

- M2 Pro MacBook Pro 16GB

- Mac Studio M4 Max 48GB

and I have not heard the fans on any of them with normal use. The only time I've ever heard automatic fans was when I was using a local 12B model on the M3 MacBook Pro, and when running 70B models on the Studio.

You should consider checking Activity Monitor and making sure that the usual suspects are not causing issues with sustained high CPU. And you can use an app like [Stats](https://mac-stats.com) if you want to see that info while actively using the computer.

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

#454

Post by psychoslave »

sanderjd wrote: post #327
psychoslave wrote: post #176

Earlier quoted context omitted.

Having to shoe a horse never was a general skill. Maybe a more apt analogy would be a skill like making fire without a lighter.

Writing software never was never a general skill either though? Or am I misunderstanding your point?

Yes, LLM are thrown through pretty much everyone digital life whether they like it or not, it's not just devs. It might even unlock exploring things that need code that average user wouldn't have dared to do before.

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

#455

Post by mashygpig »

It's fun to run a model locally, but I don't think the economics make sense for anyone just trying to use models atm. It's absurdly cheap to use the same model via openrouter in comparison.

Seriously, just put $10 into openrouter and play with models that are cheap but bigger than what you'd reasonably be able to run locally like deepseek v4 flash (unquantized). You'll be surprised by how far that $10 goes for a model better than what you'd be able to run. Even further on the model you would be able to run locally. Then think of how many long it would take to match the cost of spend + power on doing it locally...

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

#456

Post by stared »

iagooar wrote: post #199

I love my MacBook Pro M5 128GB RAM and I love qwen3.6. BUT DO NOT buy this MacBook if you plan on doing serious coding using local LLMs with it. The reason is simple: your fingers will burn and your head will explode from the noise. Running any kind of sophisticated job on the very laptop you are using is just not viable. Sure you can use it in clamshell mode, but forget touching it while working with AI coding or ag…

Yes, it gets really hot really fast.

As much as I was tempted to use it on longer projects, I had some reservations about whether it would put too much strain on my MacBook.

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

#457

Post by blagui »

How you can do dev in 2026 using 64k context and without sub agents?

The benchmark seemed fine until I saw that.

If you use sub agents, they will overwrite the cache and each request will trigger full reprocessing. Have fun with that as it will crash the t/s metrics on each prefill on top of the max 64k including input + output is a major blocker.

If you push the context higher and add parallel slots the requirements will be far higher and the numbers less shiny.

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

#458

Post by anon373839 »

lee_ars wrote: post #323
acters wrote: post #212

Earlier quoted context omitted.

Would the new upcoming AMD AI ryzen halo desktop be a better value offer? or dgx spark? You would have to get a third party reseller/scalper or refurbished mac mini to get 64gb of ram ever since apple stopped selling it.

I'm currently fiddling with a DGX Spark and Qwen3.6-35B-A3B (specifically Qwen3.6-35B-A3B-NVFP4 under vLLM, with EAGLE3 speculative decoding via eagle3-dogacel-vllm), and it's pretty okay in terms of smarts. The speed is relatively usable at about 50 tok/sec with a 256k context window, and it's definitely smart enough to one-shot some basic coding tasks. I had it doing reverse engineering/disassembly of some ancient…

I use Qwen 3.6 35B-A3B constantly, but I don’t see the type of behavior you mentioned. I’m using Unsloth’s Q8_K_XL quant.

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

#460

Post by stared »

christoff12 wrote: post #374

I just burned 20 minutes because I wanted to play hex minesweeper: https://hexabomb.pgpln.app Source: https://chatgpt.com/share/6a42dd8a-4e28-83e8-9ef7-6ba56d665c...

Nice!

If you want to play a hyperbolic minesweeper, Hyperrogue features that https://hyperrogue.fandom.com/wiki/Minefield

Post reply on HN