local intelligence

can it run

Can the NVIDIA B300 (Ultra) 288GB run llama3.1 70B?

FULL

44.2 GB needed of 288 GB usable — headroom for context

288GB · Blackwell Ultra · model file 43GB · 70B

~86–140 tok/s

computed roofline: 8000 GB/s × 0.46–0.76 efficiency window / 43.0GB (Q4_K_M) — bands, never points.

Run llama3.1 70B on instead

NIMO AI Mini PC (128GB) — cheapest catalog machine that runs llama3.1 70B fully ($1999)

NVIDIA DGX Station (GB300) — upgrade path machine

every model the NVIDIA B300 (Ultra) 288GB can run — full list

explore the full catalog90 machines indexed · live prices · what each one can run
2026-09-24 · ← all models on the NVIDIA B300 (Ultra) 288GB · fit = weights + 4k KV vs usable memory