I’d be interested in this with my ai max 395
It would be nice to use this for diffusion and audio based workflows.
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
I’d be interested in this with my ai max 395
It would be nice to use this for diffusion and audio based workflows.
Has anyone a number on theoretical compute per €? And compared with RTX 5090? Benchmarks?
Behind a 9070xt but with 32G vram
https://www.techpowerup.com/gpu-specs/radeon-ai-pro-r9700.c4290
Power consumption is relatively low in comparison to other similar cards.
It could be lower; nv48xtx shines as a 220W board. I think this xtw could work comparably well at that power envelope, though a slight bump would be wise to accommodate the additional 16GiB GDDR6 (assuming the modules are clamshelled).
fortunately it's trivial to play with the power on both windows (via adrenalin) and Linux (using something like LACT)
It kind of hurts when you put it that way. $600 for an extra 16Gb.
Sounds like nvidia. IDK why AMD copies them.
Finally!