this post was submitted on 27 Jan 2025
48 points (90.0% liked)
World News
846 readers
948 users here now
Rules:
- Be a decent person
- No spam
- Add the byline, or write a line or two in the body about the article.
Other communities of interest:
founded 5 months ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
OK, hold on, so I went over to huggingface and took a look at this.
Deepseek is huge. Like Llama 3.3 huge. I haven't done any benchmarking, which I'm guessing is out there, but it surely would take as much Nvidia muscle to run this at scale as ChatGPT, even if it was much, much cheaper to train, right?
So is the rout based on the idea that the need for training hardware is much smaller than suspected even if the operation cost is the same... or is the stock market just clueless and dumb and they're all running on vibes at all times anyway?
it does not take an entire nvidia datacenter to serve one customer. the largest model appears to run on a high end rig.
The largest model, the only one that beats GPT is like 700gb.
It’s not running on a high end rig, it’s running on a server.