Saw that DGX Spark vs Mac Mini M4 Pro benchmark plot making the rounds (looks like it came from @lmsysorg).
Thought I’d share a few notes as someone who actually uses a Mac Mini M4 Pro and has been tempted by the DGX Spark.
First of all, I really like the Mac Mini. It’s probably the best desktop I’ve ever owned. For local inference with open-weight LLMs, it works great (the plot above captures that well). I regularly run the gpt-oss-20B model on it.
That said, I would not fine-tune even small LLMs on it since it gets very hot. The DGX Spark probably targets that type of sustained workload. (From those who have one, any thoughts on the noise and heat levels?)
The other big thing that DGX Spark gets you is CUDA support. If you use PyTorch, that’s pretty essential since MPS on macOS is still unstable, and fine-tuning often fails to converge.
E.g., see
https://t.co/XSz5qcTJTX
and
https://t.co/8ASr0Q0fS8
I also like the Spark’s for factor (hey, it really appeals to the Mac Mini user in me).
But for the same money, I could probably buy about 4000 A100 cloud GPU hours, and I keep debating which would be the better investment.
Sure, I could also build/get a multi-GPU desktop. I had a Lambda system with four GTX 1080 Ti cards back in 2018, but it was too loud and hot for my office. And if I have to move it to another room and SSH into it anyway, I might as well use cloud GPUs instead?
we're going to hit a breaking point soon, idk when
but at that point, verified human internet apps are gonna start to look really, really good
and i think even a step further than that, we're probably looking at the end days of the anonymous internet for social applications
> Stop wasting time checking every registrar just to buy a domain. ⏳
> Compare prices instantly & find the best deal in minutes.
> Meet "NameHunt" - Proudly Open Source ⚡
> https://t.co/mJisiX3zgl | Full demo and repo link below ⬇️
When a model gives you the right answer to a reasoning question, you can't tell whether it was via memorization or via reasoning.
A simple way to tell between the two is to tweak your question in a way that 1. changes the answer, 2. requires some reasoning to adapt to the change. If you still get the same answer as before... it was memorization.
Got a DM: the CCP has disappeared Wenfeng for his criticism of Chinese business culture in an interview a year ago. Think about it: when has anyone last seen him? DeepSeek is headless now…
They always kill the goose that lays golden eggs. Like Jack Ma. This is why America wins.
@RealDanMcCoy@Zforever97@JanCamenisch Cool cool. But just go here https://t.co/WmovB45eoj
enter your principal and get the balance.
The cool part of blockchain is the permissionless access (dfx). But that interface is the next best thing.
No point having the NNS team endlessly build useless things.
@Zforever97@JanCamenisch You could use DFX. But easier I bet you could find the function for balance in the Dashboard under the ckUSDT canister and put in your principal and show the balance.
@Zforever97@JanCamenisch Fair. I guess I mean, why do you need to see your ckUSDT balance in NNS? Not saying it's not a fair request to expect ck Assets to be there