local intelligence

can it run

Can the NVIDIA H100 80GB PCIe run qwen2.5vl 32B?

FULL

23.0 GB needed of 80 GB usable — headroom for context

80GB · Hopper · model file 22GB · 32B

~43–70 tok/s

computed roofline: 2039 GB/s × 0.46–0.76 efficiency window / 22.0GB (Q4_K_M) — bands, never points.

Run qwen2.5vl 32B on instead

Mac mini M5 Pro (64GB) — cheapest catalog machine that runs qwen2.5vl 32B fully ($1669)

rtx-pro-6000 — the next step up from NVIDIA H100 80GB PCIe

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