[models] RTX a6000 48gb Collection Models that run well on a *standalone* RTX a6000's 48gb of VRAM. • 17 items • Updated 2 days ago • 1
view reply That's almost exactly what I'm estimating based on Deepseek R1 pulling about 1 or 2 TPS. Offloading a few layers to some A6000s didnt really help much either.
view reply I have enough DDR4 to put this on a 64 core threadripper, but I'm worried about how brutally slow it will be :)
Maia3 Collection Maia-3 is the state-of-the-art in human chess move-matching accuracy across skill levels. • 8 items • Updated Jun 23 • 7
[models] GTX 1660 Super 6gb Collection The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize. • 12 items • Updated May 29 • 2
[models] Image Generation Stack Collection The stuff we actually use, pruned on an ongoing basis. • 13 items • Updated May 29 • 1
[models] Image Generation Stack Collection The stuff we actually use, pruned on an ongoing basis. • 13 items • Updated May 29 • 1