AI brief
IBM's CEO said open weight models offer about 90 percent of the performance at roughly ten percent of the price when run on-premises in two or three racks.
Why it matters: If accurate, cheaper on-premises open weight models could make self-hosted AI more attractive than paying for hosted services.
Written by AI from The Register AI + ML's published text.
Background
From our own funding, model and news trackers, not from the source.
IBM
- Newest model on the API
- Granite 4.2 8B · 31 Aug 2026 · $0.06 in / $0.15 out per million tokens
- Last 30 days
- 12 news stories
Source
“90 percent of the performance at ten percent of the price, in just two or three racks, is hard to…”
Reporting from a publisher outside the organisation being covered.
Read original story ↗