local intelligence

can it run

Can the AMD Instinct MI100 32GB run gemma3 12B?

FULL

9.6 GB needed of 32 GB usable — headroom for context

32GB · CDNA1 · model file 8.1GB · 12B

~42–68 tok/s

computed roofline: 1228.8 GB/s × 0.28–0.45 efficiency window / 8.1GB (Q4_K_M) — bands, never points.

Run gemma3 12B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs gemma3 12B 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