walrus01

It sounds like each "MEP" (mission extension pod) once attached is its own fully autonomous satellite? How big is each MEP? Like, a mini fridge? Since the mission is designed to attach one a…

Presumably it's also known to everyone who builds/operates these that having a foreign nation's military satellite intentionally approach your own geostationary satellite to within a ve…

The new robot grappler arm definitely seems like an advancement on previous designs. The MEV was, as I recall, designed to mate with only a specific set of models of geostationary satellite bus and, f…

One of the problems in buying used/refurb x86-64 rack servers for test and development/proof of concept environment, is that by volume in the market, there's not that many -48VDC power …

> Are there? At the highest levels of defense and law, AWS and Azure are used. This is certainly true if the user is an American company. You could look at the European initiatives to run this stuf…

You seem to be categorizing everything that considers their data being in the possession of the US an unacceptable risk to be tinfoil hat, which is kind of an insult to a large portion of the world. I…

It's not exactly the first, this is the first (unclassified, that we know about) satellite to go up and grapple a satellite in geostationary and provide stationkeeping functions for it, which did…

Looks like it's live now, it's approx 17GB per safetensors file x 96 files, so so about 1.63TB. I can only imagine that people with their favorite quantizing tools warmed up and ready to go …

I am not in Quebec but Quebec hydro rate D for standard residential would be one example of around what I pay. https://www.hydroquebec.com/residential/customer-space/rates...…

The epyc Venice SP7 socket is apparently 9324 pins https://x.com/tomshardware/status/2066846693778510331 …

It's a bit worrying the author is asking chatgpt about the tingle rather than making sure there's a grounding lug on all the panels and they're all bonded to a grounding rod. The rudime…

Very good description of it. It does seem like a bit of a rhetorical question to ask a forum that has a very high population of Linux and BSD users why they might desire to have the option to do somet…

It is not my use case but given recent political developments in international relations caused by the executive branch of the US government, off the top of my head, I could think of a lot of European…

1536GB of DDR4 ECC server RAM is somewhere between $4000-6000 USD used right now, by the time you put in parallel enough NVME SSD to approach good speeds, you'd be approaching that (and also like…

Keep in mind that just because it has dual 750W power supplies that doesn't mean it's what its load will be, for a full CPU loaded wattage figure you'd need basically a pair of kill-a-w…

I think he means electrical bill at his estimated wattage load of the server and his known kWh cost, not rented server/hosting cost.

I have never seen anyone report "this produced really great results" from intentionally quantizing their context vs. leaving it at full precision which is the ordinary default.

Yeah, or close enough to 5GB for estimation purposes, for example a just spawned qwen 3.5 122B llama-server instance reports as: 0.07.015.888 I common_memory_breakdown_print: | - Host …

The cynic in me says maybe they would be further along if they hadn't spent $80 billion on trying to build the "Metaverse" VR world. I've never met anyone who actually uses it and …

Do you mean by trading dollars for the privacy you need as: a) Contracting with a third-party independent inference provider who will run your choice of model on fast hardware that they own, with all …

Recently spent a few hours messing with bonsai 27B and ternary bonsai 27B at total weights + context fitting in slightly under 6GB RAM, and it's just dumb as hell. It writes what seems like gramm…

Or 11/Shrawan 2083 if you're in Nepal

I assume you mean putting only the 32B active parameters on the GPU, and the rest on a bunch of regular server DRAM like on a 768GB to 1024GB RAM server? Because Kimi K2.6 in Q4 is about 584GB GGUF …

It's a great concept but I think it would cross the line from 'very slow' to 'so slow it's unusable' at this size. Even if we say you have an NVME SSD that does 7GB/…

Yeah, I think we will know more within a couple of days, once people actually download/run/test it. I'm sure the people adjacent to the 'heretic' developers will give it a tes…

Do I really need to? No, not really. The 27B full density, 35B MoE, 70B and 122B models I have in use get me 95% of the way there on a lot of things. Particularly when dealing with languages and sys…

Indeed not, but I was saying there's more than ample precedent which is tested/working and actually doesn't refuse anything. Go to the Huggingface 'models' search interface an…

I agree it's very likely to be painfully slow, I very much want to see some real world results from people who try it. Early testers will inform others on whether it's even worth trying. Res…

There are a number of use cases where sending the contents of your context and prompts (and the resulting output) to a 3rd party service is off the table as an option, and people will compromise speed…

I have found that the "mostly didn't lose anything" Q8 large models that I want to run are all too large to run on the "only $3995!" 128GB max RAM systems that some people are…