I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.

It's a really good drivetrain that was unfortunately made untenable for a long time by a combination of regulation and market forces.

From a pure energy efficiency perspective you can't beat economies of scale. A stationary power plant (even ones that are just big gasoline engines) run at a constant load and RPM so they can be optimized for pure efficiency, they rarely have to start, warm up, and shut down, and they can use larger and more expensive exhaust aftertreatment systems. Most energy conversions grow more efficient with scale and this is no different. The locomotive powertrain works for a handful of reasons but one of them is you can build much more efficient engines that are optimized for a single constant speed and load. But most of the advancements in internal combustion engines over the last 20-30 years don't increase peak efficiency but increase the conditions in which they're efficient. Variable valve timing and lift are probably the most underrated and overpowered technologies that have transformed engines from having one narrow regime of high efficiency to running well over a huge range of the map. But turbocharging, variable intake geometries, 7+ speed transmissions, and mild hybrid systems like belt-starter-generators get honorable mentions here. However we're not talking about anything close to EV-levels of efficiency. I think the cutting edge research engines are running in the mid to high 40s for thermal efficiency (percentage of fuel energy captured as useful work), most passenger car engines probably peak in the mid 30s.

So while there is some efficiency to be gained by a more locomotive-style system it's not as much as you would hope. In the industry that's called a series hybrid system, vs a parallel hybrid system where either ICE or EV power can go to the wheels. The benefits of a series system are more emissions and product features. You can get the full torque and power of an EV, you can start and stop the IC engine in a more emissions optimized way, and and you can filter load spikes to use a small engine that meets average not peak load.

From a more pragmatic perspective, with the energy density of gasoline and other liquid fuels it's probably best to use it in applications for which you just can't use full electrification. Planes are currently the best example of this. It's also worth noting that passenger cars benefit massively from strong hybridization because of the uneven load cycles so that's a technology where you can deploy a gasoline engine but then claw back a lot of the efficiency losses with hybrids. That's not always true, for example boats don't really have a regen cycle so hybridization just doesn't get much.

Edit: another important point is that the "cost" to acquire gasoline is only the very end of the process. The energy has already been gathered, stored, and most of the processing is complete. Our cost (in money and energy) to "make" gasoline is really just gathering it. This is why the comparison to renewables is often a hard sell, it's just apples to oranges. Gasoline started on third base, renewables are batting from the plate. Some of the internal combustion enthusiasts are holding up e-fuels or synthetic fuels as the solution but then we have to pay for the entire energy gathering and processing pipeline and still be using a conversion method that's not at all efficient. It's the worst of both worlds.

https://hannahritchie.com/

You're going to have to make a stronger case that this data is biased towards LLM than that.

I just don't see a world where that doesn't happen with Meta glasses.

Possibly the best per storage RAM price on the market right now!

Ironically, after a series of uninspiring Windows machines the next laptop that made me feel any level of enthusiasm like that Mac is my current Framework 13 running COSMIC on NixOS. Quite an about face!

If leaving out the Oxford comma here was an intentional joke I both commend and curse you!

IMO the next important unblocker for Linux adoption is the Adobe suite. In a post-mobile world one can use a tablet or phone for almost any media consumption. But production is still in the realm of the desktop UX and photo/video/creative work is the most common form of output. An Adobe CC Linux option would enable that set of "power users". And regardless of their actual percentage of desktop users, just about ever YouTuber or streamer talking about technology is by definition a content creator so opening Linux up to them would have a big effect on adoption.

And yes I've tried most of the Linux alternatives, like GIMP, Inkscape, DaVinci, RawTherapee, etc. They're mostly /fine/ but it's one of the weaker software categories in FOSS-alternatives IMO. It also adds an unnecessary learning curve. Gamers would laugh if they were told that Linux gaming was great, they just have to learn and play an entirely different set of games.

I hope maybe if we can be aware that this is a broad set of technologies being driven by a broad set of goals then we can be a bit more gracious when a project isn't perfectly aligning with our personal values and find the common ground and values.