local intelligence

can it run

Can the NVIDIA GeForce RTX 5070 run LLAMA4 Maverick 400B A17B?

NO

245.8 GB vs 12 GB usable — does not fit

12GB · Blackwell · model file 245GB · Maverick 400B A17B

~1.5–2.2 tok/s

computed roofline: 672 GB/s × 0.56–0.80 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-5070-ti — the next step up from NVIDIA GeForce RTX 5070

every model the NVIDIA GeForce RTX 5070 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 GeForce RTX 5070 · fit = weights + 4k KV vs usable memory