this post was submitted on 14 Jul 2025
47 points (100.0% liked)

Selfhosted

49590 readers
512 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

  1. Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.

  2. No spam posting.

  3. Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.

  4. Don't duplicate the full text of your blog or github here. Just post the link for folks to click.

  5. Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).

  6. No trolling.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 2 years ago
MODERATORS
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
47
Very large amounts of gaming gpus vs AI gpus (ani.social)
submitted 4 days ago by [email protected] to c/[email protected]
43 comments fedilink hide all child comments
 
GPU VRAM Price (€) Bandwidth (TB/s) TFLOP16 €/GB €/TB/s €/TFLOP16
NVIDIA H200 NVL 141GB 36284 4.89 1671 257 7423 21
NVIDIA RTX PRO 6000 Blackwell 96GB 8450 1.79 126.0 88 4720 67
NVIDIA RTX 5090 32GB 2299 1.79 104.8 71 1284 22
AMD RADEON 9070XT 16GB 665 0.6446 97.32 41 1031 7
AMD RADEON 9070 16GB 619 0.6446 72.25 38 960 8.5
AMD RADEON 9060XT 16GB 382 0.3223 51.28 23 1186 7.45

This post is part "hear me out" and part asking for advice.

Looking at the table above AI gpus are a pure scam, and it would make much more sense to (atleast looking at this) to use gaming gpus instead, either trough a frankenstein of pcie switches or high bandwith network.

so my question is if somebody has build a similar setup and what their experience has been. And what the expected overhead performance hit is and if it can be made up for by having just way more raw peformance for the same price.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 15 points 4 days ago (2 children)

You really need to elaborate on the nature of the scam.

[–] [email protected] 12 points 4 days ago (1 children)

LLMs are experimental, alpha-level technologies. Nvidia showed investors how fast their cards could compute this information. Now investors can just tell the LLM what they want, and it will spit out something that probably looks similar to what they want. But Nvidia is going to sell as many cards as possible before the bubble bursts.

[–] [email protected] 2 points 4 days ago (1 children)

so... GPU were for crypto before, now it's for LLM, weird world we live in

[–] [email protected] 3 points 4 days ago (1 children)

Any time you need a CPU that can do a shit load of basic math, a GPU will win every time.

[–] [email protected] 3 points 4 days ago (1 children)

You can design algorithms specifically to mess up parallelism by branching a lot. For example, if you want your password hashes to be GPU-resistant.

[–] [email protected] 1 points 2 days ago

And all other great reasons to use excessive branching

[–] [email protected] 6 points 4 days ago (1 children)

ML has been sold as AI and honestly that's enough of a scam for me to call it one.

but I also don't really see end users getting scammed just venture capital and I'm ok with this.

[–] [email protected] 1 points 4 days ago

Correct. Pattern recognition + prompts to desire a positive result even if the answer isn't entirely true. If it's close enough to the desired pattern, it get pushed.