top | item 46623235 (no title) teej | 1 month ago Depends how many 3090s you have discuss order hn newest woggy|1 month ago How many do you need to run inference for 1 user on a model like Opus 4.5? ronsor|1 month ago 8x 3090.Actually better make it 8x 5090. Or 8x RTX PRO 6000. load replies (2) _flux|1 month ago None, if you have time to wait, and a bit of memory on the computer.
woggy|1 month ago How many do you need to run inference for 1 user on a model like Opus 4.5? ronsor|1 month ago 8x 3090.Actually better make it 8x 5090. Or 8x RTX PRO 6000. load replies (2) _flux|1 month ago None, if you have time to wait, and a bit of memory on the computer.
woggy|1 month ago
ronsor|1 month ago
Actually better make it 8x 5090. Or 8x RTX PRO 6000.
_flux|1 month ago