211–220 of 510 posts
How about “We sell a computer called the tinybox. It comes in two colors + pro. tinybox red and green are for people looking for a quiet home/office machine. tinybox pro is for people looking for a loud compact rack machine.” [0] [0] https://tinygrad.org/#tinybox
Is there any effort in local cloud computing? I can't justify $3000 for a fun device. But if all devices (6 phone, 2 iPads, a desktop and 2 laptops) in my home can leverage that for fast LLM, gaming, and photo/video editing, now it makes so much more sense.
I'm mildly skeptical about performance here: they aren't saying what the memory bandwidth is, and that'll have a major impact on tokens-per-second. If it's anywhere close to the 4090, or even the M2 Ultra, 128GB of Nvidia is a steal at $3k. Getting that amount of VRAM on anything non-Apple used to be tens of thousands of dollars.
(They're also mentioning running the large models at Q4, which will definitely hurt the model's intelligence vs FP8 or BF16. But most people running models on Macs runs them at Q4, so I guess it's a valid comparison. You can at least run a 70B at FP8 on one of these even with fairly large context size, which I think will be the sweet spot.)
>This paper describes how the performance of AI machines tends to improve at the same pace that AI researchers get access to faster hardware. The processing power and memory capacity necessary to match general intellectual performance of the human brain are estimated. Based on extrapolation of past trends and on examination of technologies under development, it is predicted that the required hardware will be available in cheap machines in the 2020s.
and this is about the first personal unit that seems well ahead of his proposed specs. (He estimated 0.1 petaflops. The nvidia thing is "1 petaflop of AI performance at FP4 precision").
I feel this is bigger than the 5x series GPUs. Given the craze around AI/LLMs, this can also potentially eat into Apple’s slice of the enthusiast AI dev segment once the M4 Max/Ultra Mac minis are released. I sure wished I held some Nvidia stocks, they seem to be doing everything right in the last few years!
This is a genius move. I am more baffled by the insane form factor that can pack this much power inside a Mac Mini-esque body. For just $6000, two of these can run 400B+ models locally. That is absolutely bonkers. Imagine running ChatGPT on your desktop. You couldn’t dream about this stuff even 1 year ago. What a time to be alive!
Nvidia just did what Intel/AMD should have done to threaten CUDA ecosystem - release a "cheap" 128GB local inference appliance/GPU. Well done Nvidia, and it looks bleak for any AI Intel/AMD efforts in the future.
I think you nailed it. Any basic SWOT analysis of NVidia’s position would surely have to consider something like this from a competitor - either Apple, who is already nibbling around the edges of this space, or AMD/Intel who could/should? be. It’s obviously not guaranteed to go this route, but an LLM (or similar) on every desk and in every home is a plausible vision of the future.
Can one game on it? If one can skip buying gaming rig with a 5090 with its likely absurd price then this 3k becomes a lot easier for dual use hobbyists to swallow Edit 5090 is 2k
The 5090 surprised me with the two slot height design while having a 575W power budget.
Earlier quoted context omitted.
I feel like a lot of people miss that Her was a dystopian future, not an ideal to hit. Also, it’s $3000. For that you could buy subscriptions to OpenAI etc and have the dystopian partner everywhere you go.
Fun fact: Her was set in the year 2025.
Is there any effort in local cloud computing? I can't justify $3000 for a fun device. But if all devices (6 phone, 2 iPads, a desktop and 2 laptops) in my home can leverage that for fast LLM, gaming, and photo/video editing, now it makes so much more sense.
This looks like a successor to the Nvidia Jetson AGX Orin 64GB Developer Kit: https://www.okdo.com/wp-content/uploads/2023/03/jetson-agx-o... I wonder what the specifications are in terms of memory bandwidth and computational capability.
This is more accurately a descendant of the HPC variants like the article talks about - intentionally meant to actually be a useful entry level for those wanting to do or run general AI work better than a random PC would have anyways.
Earlier quoted context omitted.
There's a lot more gamers than people wanting to play with LLms at home.
There's a titanic market with people wanting some uncensored local LLM/image/video generation model. This market extremely overlaps with gamers today, but will grow exponentially every year.
Titanic - so about to hit an iceberg and sink?