local intelligence

can it run

Can the AMD Instinct MI355X 288GB run gemma3 4B?

FULL

3.8 GB needed of 288 GB usable — headroom for context

288GB · CDNA4 · model file 3.3GB · 4B

~680–1100 tok/s

computed roofline: 8000 GB/s × 0.28–0.45 efficiency window / 3.3GB (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 gemma3 4B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs gemma3 4B fully ($35)

NVIDIA DGX Station (GB300) — upgrade path machine

every model the AMD Instinct MI355X 288GB 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 MI355X 288GB · fit = weights + 4k KV vs usable memory