Hacker Newsnew | past | comments | ask | show | jobs | submit | hwertz's commentslogin

Well, just running on a 6C/12T Coffee Lake CPU, (I'm looking through these speeds in LM Studio as I type this..) I got like 2 tokens a second with Deepseek R1 14B, 3.4 with 7B Qwen, and 4.4 with 8B Llama, although out of those two I found 7B Qwen's answer to be a bit better. (My GTX1650 has 4GB VRAM, loading 1/4 the layers is pretty ineffective, GPU util went up to 10% and I gained like 1 token a second LOL.)

So it'd take a minute or two to type out one of those answers where it's got about 4 or 5 beefy paragraphs of thought and a decent sized paragraph for it's answer. I'll put it this way, I can type 120 WPM and it puts out text a bit faster than I could write it.

Input's a LOT faster though, I was asking these models to analyze a document so my input was like 2200 tokens, they all did well over 100 tokens a second on input.


Nope, I read The Register (UK based) and they've had scandals from celebrities having their confidential SMS messages leaked; SMS spoofing; I think they even have SIM cloning going on every now and then in UK and some European countries. (since The Register is a tech site, my recollection is some carriers took technical measures to prevent these issues while quite a few didn't.)

I don't think it's a thing that happens that often in UK etc.; but, it doesn't happen that frequently in the US either. It's just a thing that can potentially happen.


UK has plenty of other problems to solve first with identity thief.


...where identity is proved by utility bills instead of government issued id


How else do you prove you live some place?

“I pay the bills there” is barely better than nothing, though. We do this in Canada too. It is what I used for a driver’s license one renewal.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: