local intelligence

can it run

Can the NVIDIA H100 80GB SXM run llava 7B?

FULL

6.7 GB needed of 80 GB usable — headroom for context

80GB · Hopper · model file 4.7GB · 7B

~330–540 tok/s

computed roofline: 3350 GB/s × 0.46–0.76 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run llava 7B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs llava 7B fully ($35)

H100 80GB PCIe (used) — upgrade path machine

every model the NVIDIA H100 80GB SXM 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 H100 80GB SXM · fit = weights + 4k KV vs usable memory