111–120 of 722 posts
Earlier quoted context omitted.
2k Usually refers to 2560x1440. 1920x1080 is 1080p. It doesn't make a whole lot of sense, but that's how it is.
https://en.wikipedia.org/wiki/2K_resolution
Earlier quoted context omitted.
2k usually refers to 1080p no? The k is the approximate horizontal resolution, so 1920x1080 is definitely 2k enough.
2k Usually refers to 2560x1440. 1920x1080 is 1080p. It doesn't make a whole lot of sense, but that's how it is.
I think a graphics card tailored for 2k gaming is actually great. 2k really is the goldilocks zone between 4k and 1080p graphics before you start creeping into diminishing returns.
2k usually refers to 1080p no? The k is the approximate horizontal resolution, so 1920x1080 is definitely 2k enough.
“2K” is used to denote WQHD often enough, whereas 1080p is usually called that, if not “FHD”.
“2K” being used to denote resolutions lower than WQHD is really only a thing for the 2048 cinema resolutions, not for FHD.
Earlier quoted context omitted.
This is the most script kiddy comment I've seen in a while. llama.cpp is just inference, not training, and the CUDA backend is still the fastest one by far. No one is even close to matching CUDA on either training or inference. The closest is AMD with ROCm, but there's likely a decade of work to be done to be competitive.
Inference on very large LLMs where model + backprop exceed 48GB is already way faster on a 128GB MacBook than on NVidia unless you have one of those monstrous Hx00s with lots of RAM which most devs don't.
A dev, if they want to run local models, probably run something which just fits on a proper GPU. For everything else, everyone uses an API key from whatever because its fundamentaly faster.
IF a affordable intel GPU would be relevant faster for inferencing, is not clear at all.
A 4090 is at least double the speed of Apples GPU.
Earlier quoted context omitted.
M3/M4 Max MacBooks with 128GB RAM are already way better than an A6000 for very large local LLMs. So even if the GPU is as slow as the one in M3/M4 Max (<3070), and using some basic RAM like LPDDR5x it would still be way faster than anything from NVidia.
Are you suggesting that Intel 'just' release a GPU at the same price point as an M4 Max SOC? And that there would be a large market for it if they did so? Seems like an extremely niche product that would be demanding to manufacture. The M4 Max makes sense because it's a complete system they can sell to Apple's price-insensitive audience, Intel doesn't have a captive market like that to sell bespoke LLM accelerator ca…
Earlier quoted context omitted.
Just how "basic" do you think a GPU can be while having the capability to interface with that much DRAM? Getting there with GDDR6 would require a really wide memory bus even if you could get it to operate with multiple ranks. Getting to 128GB with LPDDR5x would be possible with the 256-bit bus width they used on the top parts of the last generation, but would result in having half the bandwidth of an already mediocre…
M3/M4 Max MacBooks with 128GB RAM are already way better than an A6000 for very large local LLMs. So even if the GPU is as slow as the one in M3/M4 Max (<3070), and using some basic RAM like LPDDR5x it would still be way faster than anything from NVidia.
12GB max is a non-starter for ML work now. Why not come out with a reasonably priced 24gb card even if it isn't the fastest and target it at the ML dev world? Am I missing something here?
12GB max is a non-starter for ML work now. Why not come out with a reasonably priced 24gb card even if it isn't the fastest and target it at the ML dev world? Am I missing something here?
Earlier quoted context omitted.
M3/M4 Max MacBooks with 128GB RAM are already way better than an A6000 for very large local LLMs. So even if the GPU is as slow as the one in M3/M4 Max (<3070), and using some basic RAM like LPDDR5x it would still be way faster than anything from NVidia.
Are you suggesting that Intel 'just' release a GPU at the same price point as an M4 Max SOC? And that there would be a large market for it if they did so? Seems like an extremely niche product that would be demanding to manufacture. The M4 Max makes sense because it's a complete system they can sell to Apple's price-insensitive audience, Intel doesn't have a captive market like that to sell bespoke LLM accelerator ca…
CPUs and GPUs access memory very differently.