Nvidia GeForce GTX 1080 Ti

I used my 1080 Ti for about eight years. The successor GPU is in some ways way faster (raytracing, AI features etc.), but in others really quite stagnant considering the huge stretch of time that passed between them. ~10 years for 2-3x performance in GPUs at higher nominal and real price points shows how slow silicon advances have been compared to the 90s and 2000s. The same period from 2000 to 2010 would've seen 1000x performance if not more. The difference between a 1080 Ti and a more expensive RTX 50 card is the RTX can render ideally triple the frames in synthetic benchmarks, double the frames in some rasterizing games (most games won't see gains that high), and do a few relatively tame raytracing tricks at performance which is still not really good. At the same throughput it consumes maybe half the power or a bit less. The difference between a GeForce 2 and e.g a Radeon HD 4k is several planes of existence.

The correct calculation is not 900€/36 months but (900€-$resell_value)/36 months. If you sell your GPU for 450€ after three years you saved a good bit of money. If the AI bubble doesn't pop, your resale value might even be a good bit higher than that. I've had a used 1080TI that I used for five years and then sold for nearly the same price, making it effectively free (minus electricity use and opportunity cost)

My 1080ti is still working away in my kid's PC. If you connect a 1080p monitor, it will still hit 60fps in mostly everything. The only thing that holds this card back now is a handful of titles that will not run unless ray-tracing support present on card - Indiana Jones and The Great Circle springs to mind etc. I am very likely going to get a decade of use out of it across three different builds, one of the best technology investments I've ever made.

Yea, it’s anecdata, but I only replaced my 1080 ti about 1.5 years ago. Graphical fidelity is at the point that unless some new technology comes out to take advantage of GPUs, I don’t see myself ever upgrading the part. Only replacing it whenever it dies. And that 1080 ti isn’t dead either, I passed the rig onto someone who wanted to get into PC gaming and it’s still going strong. I mostly upgraded because I needed more ram and my motherboards empty slots were full of drywall dust. The phone I’m more liable to upgrade solely due to battery life degradation.

This is Black Friday pricing at least, if you're willing to shuck. Seagate drives are still sub-$10/TB which... a single 24-26TB is enough for all my photos (ever), media and some dataset backup for work. I'm planning to backup photos and other "glacier"-tier media like YouTube channels to BluRay (a disk or two per year). It's at the point where I'd rather just pay the money and forget about it for 5-10 years. I built the case from Makerbeam and printed panels, an old Corsair SF600 and a 4 year old ITX system with one of Silverstone's backplanes. They make up to 5 drives in a 3x5-1/4 bay form factor. It's a little overpowered (a 5950X), but I also use it as a generic server at home and run a shared ZFS pool with 2x mirrored vdevs. Even with inefficient space it's more than I need. I put in a 1080ti for transcoding or odd jobs that need a little CUDA (like photo tagging). Runs ResNet50-class models easily enough. I also wondered about treating it as a single-node SLURM server.

Really depends on where you're located and what kind of cheap we're talking about. For instance, I buy the overwhelming majority of my equipment used or refurb -- anywhere from Amazon (warehouse deals) to Microcenter / Newegg (open box) to Ebay to sites like PC Server and Parts [0]. I also frequent thrift stores (got a perfectly good Epson Workforce 1100 for $9, just needed ink and a little love). I will say that for some of it, stuff in the "really-cheap-in-comparison-to-MSRP, but still money" category, buying from a vendor that specializes in refurb/off-lease is a safer bet than a mishmash of Ebay parts just in the event that a given component is bad or unreliable. For instance, I recently put together a dual-Xeon box and the riser board was damaged in some way I couldn't repair; PCSP sent me a new one, problem solved. Would've been fairly costly had that been an Ebay buy (especially from a Chinese vendor, the shipping now! my god). All-in, I ended up with case, power supply, riser board, 2x E5-2667v4 CPUs, 256gb ram, GTX 1080ti for like $490. After using some other recycled parts and then selling some old stuff on Ebay, I ended up with a new computer for like 350 bucks... and for being essentially 10 year old equipment, it's shockingly performant. You just never know what you'll find! It takes time to research and decide what you actually want, then locate it at a good price, so you better be in love with the hunt hahaha. [0] https://pcserverandparts.com

I have a machine with 3 108 TI's that I do a batch with, sending the question first to a LLM and then an LRM, returning to review the faster results and killing the job if they are acceptable. Ollama or just llama.cpp on podman makes this trivial. But knowing* what model will be better will be impossible, only broad heuristics that may or may not be correct for any individual prompt could be used. While there are better options if you were buying them today, an old out of date system with out of date GPUs works well in this batch model. gemma-3-27b-it-Q6_K_L works fine with these, and that mixed with an additional submit to DeepSeek-R1-Distill-Qwen-32B is absolutely fine on that system that would just be shut down otherwise. I have a very bright line about inter-customer leakage risk prevention that may be irrational but with that mixture I find that I am better looking at scholarly papers than trying the commercial models. My primary task is FP64 throughput limited, and thus I am stuck on Titan V as it is ~6 times faster than the 4090 and 5 times faster than the 5090 is the only reason I don't have newer GPUS. You can add 4 1080ti at 200w limit with common PSU's and get the memory, but performance is limited by the pci bus at 3 1080ti. As they seem to sell for the same price, I would probably buy the Titan V today, but the point being is that if you are fine with the even smaller models, you can run them queries in parallel or even cross verify, which dramatically helps wi…

1080Ti from 2017 still handles modern AAA games really well, was able to play and finish Cyberpunk 2077 with no issues. Really a remarkable feat of engineering for it's time.

In your experience for sure, myself and everyone I know with a desktop upgrades bit by bit where they can. My recent one was 16->32gb ram, even cheaper now since it's only ddr4. Tho the next will likely be a full upgrade as my last main build was 2018 with the mini-itx I still have. But if I want to do more ai stuff I'll probably need to hop up to m-atx or even just atx. 1080ti I'm currently on was the last before the era of sanely sized gpus came to an abrupt end

> Comparing ... might be more fair, I don't make purchasing decisions based on what's 'fair', I look at what capabilities I have, what I lack, and what my budget is. > Why does that seem the same to you? Exchange rate. But you make a valid point that I should also factor in inflation. > We’re in a ray tracing thread and for ray tracing, there’s no contest, the 4060ti wins there by a long way. It wins in the sense that it can do ray tracing while the 1080Ti cannot, but based on my understanding, the xx60-tier cards aren't viable for raytracing at 60fps without DLSS anyway, and I'm still not convinced I want to consider DLSS performance to be the number I care about in my purchasing decisions. > UserBench says today the 4060ti is 17% faster for 20% lower price today, The most important question I look at is "what games can I run at what resolution" and I don't think there's a single game I can get acceptable performance at 4K on a 4060Ti or even a 4070, that I can't get acceptable 4K performance on a 1080Ti. There are probably a couple that I could run at 1080p that I have to run at 720p currently. I'm not using a variable/high refresh rate monitor and i'm not playing competitive shooters.

I would prefer that this become the standard for software, as a whole, to be open source after a while. Because there is a sustainability aspect, just like the rest of the tools in our world. For example, a manual drill has no real draw backs it will always run. An electric drill with a cord, will likely always run and electrical components can be traced and sourced rather easily. A drill that was designed to use with a battery, will not always run, and has software/firmware with some other limitations likely buried in the software. The moment support is dropped, it should be released to open source to allow others interested to maintain it. Such as with the Nvidia Geforce GTX 1080 Ti... no longer supported with driver updates (outside of "security updates"). The firmware should be supported by the people if the company doesn't want to support it, it still is an excellent card even 10 years later... MMO or not, source code should just be released. Patents are not forever, source code shouldn't be either. Though patent might be too long as well. 15/20 years worked when things developed slowly, but now days its outdated within years and could benefit other advancements.

It's amazing how great the 10 series was. The 1060, a budget card, had the same amount of VRAM as the previous generations top tier card (6GB) with the 1080Ti having 11GB ! the 5060 for example has only 8GB, the same as the GTX 1070 and 1080.