local intelligence

can it run

Can the AMD Instinct MI100 32GB run qwen3 8B?

FULL

5.8 GB needed of 32 GB usable — headroom for context

32GB · CDNA1 · model file 5.2GB · 8B

~66–110 tok/s

computed roofline: 1228.8 GB/s × 0.28–0.45 efficiency window / 5.2GB (Q4_K_M) — bands, never points.

Run qwen3 8B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs qwen3 8B 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