You could probably run a Q2-Q3 with 2x DGX Sparks. So...$12k at today's prices. Plenty of folks are running DS 4.1 Flash with Strata and some GPU + bulk in system memory. Maybe more like $3k-$4k? But speeds come down quite a bit.

▲

lupodevelop a day ago | parent | next [-]

[flagged]

▲

joshspankit 19 hours ago | parent | prev [-]

Q2. Woof.

	▲	colingauvin 18 hours ago \| parent [-]
		It actually benchmarks quite well. Honestly not practically worse than the Q4 native weights.