731–740 of 1001 posts
Earlier quoted context omitted.
Another commenter stated the P cores can be scaled down to be E cores dynamically, so why not?
I wonder if they'll get to good enough scaling from E to Super where they don't really need to distinguish anymore?
Earlier quoted context omitted.
It won’t handle serious tasks but I have Gemma 3 installed on my M2 Mac and it is good for most of my needs—-esp data I don’t want a corporation getting its hands on.
What kind of tasks are you using it for? I haven't really found any uses for small models.
Earlier quoted context omitted.
With OpenClaw and powerful local models like Kimi 2.5, these specs make a lot of sense.
K2.5 isn't remotely a local model
I have a fairly maxed out M2 Ultra (24 cores, 192GB RAM), and still cannot get this machine to choke on anything. I have not once felt the need to upgrade in years, and that’s with doing pretty demanding 3D and LLM work.
Earlier quoted context omitted.
>Time to first token measured with an 8K-token prompt using a 14-billion parameter model with 4-bit quantization Oh dear 14B and 4-bit quant? There are going to be a lot of embarrassed programmers who need to explain to their engineering managers why their Macbook can't reasonably run LLMs like they said it could. (This already happened at my fortune 20 company lol)
I don’t really get why people are smack talking this, are there other laptops available that can do better?
Earlier quoted context omitted.
14-billion parameter model with 4-bit quantization seems rather small
For anyone who has been watching Apple since the iPod commercials, Apple really really has grey area in the honesty of their marketing. And not even diehard Apple fanboys deny this. I genuinely feel bad for people who fall for their marketing thinking they will run LLMs. Oh well, I got scammed on runescape as a child when someone said they could trim my armor... Everyone needs to learn.
Earlier quoted context omitted.
It won’t handle serious tasks but I have Gemma 3 installed on my M2 Mac and it is good for most of my needs—-esp data I don’t want a corporation getting its hands on.
What kind of tasks are you using it for? I haven't really found any uses for small models.
Nano-texture is worth the upgrade if you are on a macbookpro whatever M and dont have it. For those of us with astigmatism it's really night and day experience.
I was considering it but got cold feet when I've been told that you could damage it when cleaning it. When I open/close my laptop I leave a ton of finger prints. I'm not too good with delicate hardware stuff.
Earlier quoted context omitted.
Mine still runs like the first day I had it. There's basically nothing that is limiting me with the machine as it is, everything is just me being slow to code. I don't see why I need a new computer at the moment. In the past, I always got to a stage where the machine felt sluggish.
Yeah my M1 is still insanely snappy. Would be nice to have some extra legroom for things like compilation, but I'm far from feeling this device isn't sufficient for me.