walrus01

what quantization? what temperature?

Biggest lesson of Jurassic Park: Don't hire only one sysadmin

It might be less about quality degrading, but on multi-user platforms running the model, they have an economic incentive to have each user not fill up the full size of the context cache. Filled contex…

I don't think you're wrong that tiny pacific island nations are not stable or reliable, at this point they're all either a client state of China, the USA or Australia. But I think it&…

> American business based in America and doing business that benefits American citizens, rather than some random banana republic. This makes a huge presumption of rock solid stability of political&…

.is might be a choice, since archive.is continues to be available despite many legal threats You don't have to be an Icelandic national to register a .is

I didn't mean so much that it was a problem, but actually in some projects for exploring what's possible, watching its "thinking" mode output at temp 0.4 is intentional and useful …

Being a prophet is probably great until you suddenly find yourself building a fortified compound in Waco, Texas and purchasing black market full auto machine guns.

Somewhat surprised they're showing the decimal 10 hour clock without mentioning French Revolutionary Time https://en.wikipedia.org/wiki/Decimal_time …

Something I've noticed is that if you run Qwen 3.6 35B-A3B (Q8) with a low temperature of 0.4, and leave default reasoning turned on, it will spend quite a lot of time in reasoning/thinking …

big number goes up and becomes larger number, chart goes up and to the right, this must be a solid measure of progress in society.

"All these GPUs are yours, except Europa. Attempt no landing there".

I've read the entire series of Culture novels and don't recall seeing "starmind" as a term anywhere. Mind, yes, but used in a somewhat different context, as the minds are both sen…

I'm curious, where are you seeing M.2 2230 to M.2 2280 size NVME SSE that exceed 4.5 to 5GB/s sequential reads for large files such as a GGUF (likefrom an ordinary ext4fs file system with de…

Unfortunately we're much too late for realnetworks and realplayer to be relevant anymore.

For one, doing the math on what it costs to rent a 768GB+ RAM AWS system with 40+ high performance CPU cores makes it very unappealing to pay for 12, 24, 36 months of it. The largest high performance …

from the article: > So space considerations were very real when a large part of your customer base existed on 300 & 1200bps modems in the mid 90’s. I somewhat did a double take at this. My fami…

I realized I didn't answer the CPU question, as a very quickly chosen example from eBay, there's a Dell R740XD with two Xeon Gold 6254 CPUs, 768GB RAM for sale for something like $5799 USD…

I was just using that as an example of constant on going price rises, it was the most mundane and not particularly fast ddr5 6000 stuff. The 6400 is even more ridiculous.

I think there is a good sized population of people who absolutely don't want to submit everything they do to an off site service, or let their content be used for unknown training purposes, and w…

Most any ticketing system can integrate with ordinary IMAP and smtp email flow, so you can really use any agent that can "do" inbound and outbound email to talk to a self hosted ticket queue…

For 10k you can buy a used dual socket Intel or amd based rackmount server with a terabyte of ram, and run models on cpu only at a reasonable speed. Same server would have been 4-5k a couple years ago…

The very boring pair of two 16GB ddr5 6000 I had in my newegg shopping cart went from $399 to $475, so increasingly the answer will be "no".

Q8 isn't overkill if you have sufficient RAM to fit the whole model, and you care about quality. There's a number of people who have enough hardware to fit exactly one 27B to 35B size Q8 mod…

At least on Android there's a fair number of apps like "osmand" which can download an entire state, province or country vector/map data, in their own semi-proprietary data format d…

MDM is designed for corporate owned phone environments where there's a great many good reasons to lock down a phone. If you're handing out company owned phones to employees you want the abil…

I think if you had something like a theoretical used/refurb 2U rackmount server with two older multi core CPUs, 768GB of RAM, you would see faster performance loading a Q6 or Q8 GGUF of GLM5.2 in…

Another thing that seems to be disturbingly common these days is some party involved in residential real estate transactions having a RAT on one or more PCs, and/or compromised email account, int…