GTX 1080s: Testing a Legend

Post by epolanski » Sun, Jul 19, 2026, 8:37 AM UTC

onli wrote: post #22

epolanski wrote: post #15

What's legendary about the 1080? It's a smaller 980ti on a much smaller node.

Less energy usage, more vram, faster in games (see https://www.pc-kombo.com/us/benchmark/games/gpu/compare?ids%... ). But it is even more about timing. Nvidia shifted to RTX afterwards, opting to go for raytracing and upscaling instead of making strictly faster cards. Which made the last GTX cards very competitive for regular usage, raising its status.

Post by weezing » Sun, Jul 19, 2026, 9:17 AM UTC

WarOnPrivacy wrote: post #42

the legendary Core i7-8700K This might be a unique assessment. My perspective is that Intel's strong lines were 4th gen and then 12th gen. I see a number 4770 and 4790 still doing the job they were bought for. I expect the same for 12th gen when they're 13yo. Not so for anything between 4th and 12th.

Post by 0x6c6f6c » Sun, Jul 19, 2026, 2:23 PM UTC

SyzygyRhythm wrote: post #38

leoqa wrote: post #23

I have 3 3090s, all in various gaming computers. I’m not sure what to do with them- the VRAM is only 24GB so doesn’t seem worth the power costs to run an open weight model. Any suggestions on how I can run them as some type of cluster? Is it worth exploring NVLink?

As others said, you can run more than one at a time, but even singly, 24 GB can be very useful in a hybrid approach. For instance, I recently had to process hundreds of high-res blueprints. Used Fable for the main orchestration, but all of the OCR and other work I did with a small local model. Didn't waste expensive Fable tokens on simple grunt work.

Post by kennywinker » Mon, Jul 20, 2026, 5:08 AM UTC

iammjm wrote: post #16

Funny enough, I have the 1080 and I tested qwen 3.5 9b on it today. I was positively surprised with the experience. It's no Opus but it did OK on the couple of queries and tasks I gave it. It's pretty impressive for a 10 year old gpu!