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

41–50 of 809 posts

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

#41

Post by Catloafdev »

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 model they reference can be easily run with 24gb+ of VRAM, and there are other similar models capable of running easily on 16gb of VRAM. It's not like 128gb is a requirement here.

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

#44

Post by DenisM »

ascii0eks84 wrote: post #18

Very capable lora adapters are surfacing but it seems they are very niche.

Can you share more? It’s the first I hear of lora outside research papers. Practical applications would be great to see.

Lora if effective could be a great reason to run local models.

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

#45

Post by Insanity »

petilon wrote: post #36
Insanity wrote: post #30

Earlier quoted context omitted.

But you have to factor in that this device will last you 5-10 years. That said, I wouldn't spend almost $7k USD on this macbook lol.

Memory requirements of newer models will increase, so while the hardware may last 10 years it won't be able to run the latest models for 10 years.

You raise a fair point, but I'm not convinced it'll offer a meaningful difference in performance as long as we're stuck with the current AI paradigm.

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

#46

Post by oldfuture »

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...

a lot of credits? we can’t predict any price change for them

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

#47

Post by __s »

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?

I'm on 128GB ram strix halo, bought framework desktop for a few thousand CAD back when everyone was calling framework desktop overpriced

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

#48

Post by kllrnohj »

h4ny wrote: post #37
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...

[flagged]

> maybe tell us how much a non-Apple system that you can run that (probably similarly or faster) would cost?

Ryzen AI Max 395+ with 128GB of unified memory can be found around $3-4k.

But 27B isn't that large, either, especially if you are ok with the quantized models. So this laptop choice seems to more be a "because they had it" rather than "this is what's necessary for this particular workflow"

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

#49

Post by simonw »

petilon wrote: post #36
Insanity wrote: post #30

Earlier quoted context omitted.

But you have to factor in that this device will last you 5-10 years. That said, I wouldn't spend almost $7k USD on this macbook lol.

Memory requirements of newer models will increase, so while the hardware may last 10 years it won't be able to run the latest models for 10 years.

It can't run the latest models today - GLM-5.2 class models already need 1TB+ of RAM.

... but, the models that WILL run on 128GB (or 64GB or even 32GB) models today are a huge improvement on the best models that would run in the same amount of memory six months ago.

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

#50

Post by dofm »

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 that.

I totally struggled to find the right frame of mind to explore any of this stuff without feeling defeated and bamboozled. Because it's just huge, exhausting, jargon-drenched, unknowable, and I am over the hill at fifty-plus.

Until, that is, I could poke around with setting it up on my own (secondhand) machine, watching the API calls, understanding some of the terminology. I didn't even buy the machine for that; it's just adequate to the task.

The Neo is too small to really get much benefit from this opportunity to make it more visceral and knowable.

Post reply on HN