#🔒 GPU(s) for tensorflow model training

9 messages · Page 1 of 1 (latest)

zealous parrot
#

would dual 4060 ti cards (16gb VRAM each, so 32GB VRAM total) be any use, considering the value for money
for model training? Or should I go for a single 3090 card? Would the 4080 be any good, considering its lower VRAM but higher speed?

raw hearthBOT
#

@zealous parrot

Python help channel opened

Remember to:

  • Ask your Python question, not if you can ask or if there's an expert who can help.
  • Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
  • Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.
runic lagoon
#

I'd go with the two 4060 ti's

#

if you're training on both you'll probably get about comparable performance to the 3090 with an extra 8gb of memory

#

most models use 32 bit float precision by default, just fyi for those charts the 32 bit tflops are usually what you're gonna be working with

#

forgot to add the tensor and rt cores for the 4080

image.png
raw hearthBOT
#
Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.