191–200 of 581 posts
Earlier quoted context omitted.
Microsoft is sleeping on Qualcomm with their lousy port of Windows to Arm processors…
10000000x this. They have been sleeping on Arm since windows phone. I just don’t see them ever having an original thought again. They could have had a 128core arm chip by now.
The Qualcomm Snapdragon X2 Elite Extreme trounces Nvidia's chip in single core CPU performance. It beats Intel and AMD's best, too. It has unified memory. It's the only CPU in the same league as Apple's M-series in both CPU performance and power efficiency. And it's available in laptops today, not later this year. People are sleeping on Qualcomm.
Is it well supported under Linux?
"I am not sure how many people will run AI models locally. It still seems like a niche application to me. However, it will make decent machines to play video games." I don't know who will be the winner but with some of the recent releases from gemma it seems more probable that you may run some models locally if only from a cost perspective, not even considering business security. Not sure how this type of architectur…
> you may run some models locally if only from a cost perspective I have a hard time believing running a model on a laptop will be cheaper than running it in a datacenter. Why wouldn't economies of scale apply here as with every other computation?
Earlier quoted context omitted.
If you could buy a 256GB you’d be claiming that 256GB is a sweet spot. But I agree with you. Crack-tokens are not the future.
no, the fact that MACs and x86 and soon ARM are all going to have 128GB models in every sector, yeah, sure. But watching everyone flounder because claude goes down or forcing you on API costs. I'm programming things that'd take me days with a PC that, without OpenAI's VRAM shenagans, would cost you $2k. It's more than just 'this is what I could do' it's definitely about 'this is what anyone could do with a new PC pur…
Earlier quoted context omitted.
My local AI is currently upscaling an old british comedy from sub-dvd quality to 1k. (It is not availible other than on DVD.) It looks like it will take about a week for my pair of 5060s to chew through the task.
Which show?
I own the DVDs so I'm OK upscaling/editing my own copies for my own use. But if I ran the task on an ai service I would no doubt trigger copyright issues.
The Qualcomm Snapdragon X2 Elite Extreme trounces Nvidia's chip in single core CPU performance. It beats Intel and AMD's best, too. It has unified memory. It's the only CPU in the same league as Apple's M-series in both CPU performance and power efficiency. And it's available in laptops today, not later this year. People are sleeping on Qualcomm.
[flagged]
The reality is even cutting edge games and consumer workloads don’t actually take full use of the PCIe bandwidth of the GPU or the bandwidth of its GDDR memory. Even local AI use cases don’t substantially or meaningfully benefit from faster memory, at least to average consumers.
A unified memory pool does two things:
1) Lets systems optimize utilization based on need, rather than be confined to specific pools
2) Reduce overall memory cost, by letting system builders purchase a single type of memory in bulk instead of having to figure out GDDR vs DDR memory placement (important for SFF/portable machines)
So at a time when memory is expensive, unified pools make more sense. Even when memory becomes cheap and plentiful again, it’s just practical at this point to allocate a larger overall pool instead of managing discrete sets.
The one big drawback is security. A shared memory pool means side-channel attacks against memory from the GPU or CPU could potentially compromise the other as well, meaning memory-safe designs are going to be critical to security going forward (which is good for Rust adherents, I figure).
Here is the press release for the actual machine: https://nvidianews.nvidia.com/news/nvidia-microsoft-windows-... I have been somewhat surprised at the lack of commentators observing that this is Microsoft and above all NVIDIA launching a device that is fundamentally at odds with the metered cloud model of AI. When you look at the other announcements and murmurings (better offline BYOK for Copilot, talk of an unmeter…
Yeah, "unmetered intelligence" was probably the most used phrase at MS BUILD this past week. They are going hard into local AI
Copilot just got proper "offline" BYOK support, didn't it? Presumably that was one of the things they were talking about. Though I imagine that has something to do with the fact that Zed has supported that properly for months.
And who in 2026 is still anal-fixated on a "Windows" PC? It's just a personal computer. It normally runs multiple operating systems just fine. Windows PC sounds like people talking about tech who are either payed by M$, or embed pictures into Word documents to send them. Nobody has to kill the fun those OS agnostic machine allow, by artificially bind them to a shitty OS.
Hopefully anyone who wants to run anything other than Windows on an Nvidia-produced device has learned their lessons at this point. Although, a cursed Nvidia Hackintosh would be extremely funny. For normal people, there are three computer operating systems: Windows, Apple, and ChromeOS. Nvidia isn't going with ChromeOS and Apple hates their guts, so Windows is the only normal operating system they can market. Their m…
I did this for years. We ran Resolve color correction suites with external chassis to place multiple Nvidia GPUs in it at a fraction of the cost of the shitty TrashCanMac that was available. Lots of people continued to use the 2012 Cheese Grater MacPro with its older CPUs. The only way to get modern (at the time) compute in a Mac was to use a Hackintosh. Since it wasn't for personal use, not having things like AppStore, Messages, Music, etc wasn't a big deal, so building a Hackintosh was easier.
I built one for personal prosumer use around the time of the 1080s that allowed me more machine for the dollar than Apple offered. Once the M-series chips came out and they were capable of what the Hackintosh was doing for me put me off of building anything newer.