I was looking into this for LLMs but it's clearly a graphics-processing focused card. The memory bandwidth is too low for that much RAM to be useful in an LLM context. The 5090 I have has the same amount of RAM but far more bandwidth and that makes it much more useful.

▲

Mindless2112 11 hours ago | parent | next [-]

Compared to a B70, a 5090 is 1x the memory with 3x the bandwidth at 4x the price. Yeah, the 5090 is better, but you're paying for it.

▲

arjie 7 hours ago | parent [-]

On actual market it’s $1100 vs $3200 now, right? I actually got mine at $2200 at cost in the before days.

▲

Mindless2112 7 hours ago | parent [-]

Current lowest price for a new card on Newegg: $949.99 vs $3,699.99.

	▲	arjie 7 hours ago \| parent [-]
		Wow, 5090 prices have exploded. Thanks for looking. I should have known by hardware price intuition is broken.

▲

girvo 11 hours ago | parent | prev | next [-]

Oh wow, I really would've expected higher memory bandwidth. That's only ~2-3x the little DGX Spark-alike I have to play with. Would've expected more.

▲

cmxch 11 hours ago | parent | prev [-]

It’s 32gb for people who can’t go for scalped 5090s but have a 3090 budget.

I have a pair of them with a 9480 and the only thing I have to do is keep the cache happy.

▲

fluoridation 11 hours ago | parent | next [-]

Eh. Trading CUDA for 8 more gigs seems like bad deal, unless you know absolutely for certain what you want to run will run on it.

	▲	cmxch 10 hours ago \| parent [-]
		Until NVidia prices get better, I’ll build out with the Intel stack and keep the cache (and prompt processing speeds) happy. As for software, anything that has a SYCL or Vulkan backend, and/or can be Intel optimized (especially to the same degree as llama.cpp) can run well.

▲

arjie 7 hours ago | parent | prev [-]

[dead]