local intelligence

can it run

Can the AMD Instinct MI100 32GB run llama3.2 3B?

FULL

2.4 GB needed of 32 GB usable — headroom for context

32GB · CDNA1 · model file 2.0GB · 3B

~170–280 tok/s

computed roofline: 1228.8 GB/s × 0.28–0.45 efficiency window / 2.0GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).

Run llama3.2 3B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs llama3.2 3B fully ($35)

A100 80GB (used) — upgrade path machine

every model the AMD Instinct MI100 32GB can run — full list

explore the full catalog90 machines indexed · live prices · what each one can run
2026-09-24 · ← all models on the AMD Instinct MI100 32GB · fit = weights + 4k KV vs usable memory