▲ local intelligence

can it run

Can the NVIDIA RTX 3090 run LLAMA4 Maverick 400B A17B?

NO

245.8 GB vs 24 GB usable — does not fit

24GB · Ampere GA102 · model file 245GB · Maverick 400B A17B

~1.8–2.9 tok/s

computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 245.0GB (Q4_K_M) — bands, never points.

Run LLAMA4 Maverick 400B A17B on instead

→ ASUS ExpertCenter Pro ET900N G3 (GB300) — cheapest catalog machine that runs LLAMA4 Maverick 400B A17B fully ($60000)

→ rtx-5090 — the next step up from NVIDIA RTX 3090

→ every model the NVIDIA RTX 3090 can run — full list

→explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the NVIDIA RTX 3090 · fit = weights + 4k KV vs usable memory