local intelligence

can it run

Can the Radeon RX 9070 XT (16GB) run LLAMA4 Maverick 400B A17B?

NO

No. 16GB of memory can't hold the 307GB working set this model needs. A smaller quant or a bigger machine is required.

~1.4–2.2 tok/s

weights 245GB + KV cache 0.75GB at 4k context vs ~16GB usable → no. 245.8 GB vs 16 GB usable — does not fit

computed roofline: 644.6 GB/s × 0.55–0.82 efficiency window / 245.0GB (Q4_K_M) — bands, never points.

explore the full catalog84 machines indexed · live prices · what each one can run

Specs

model file245GB (GGUF Q4_K_M)
minimum memory307GB working set
this machine16GB GDDR6
paramsMaverick 400B A17B
licensellama4 (gated on HF)
price$749

Run it

model files: hugging face ↗

easy run: ollama pull llama4:maverick

runs with: ollama · llama.cpp · koboldcpp · lm studio

Alternatives

ASUS ExpertCenter Pro ET900N G3 (GB300) — cheapest machine that runs it ($60000)

every model the Radeon RX 9070 XT (16GB) can run — full list

Radeon AI PRO R9700 (32GB) — upgrade path machine

Buy

Newegg ↗ · Amazon ↗ (affiliate)

2026-09-17 · ← all models on the Radeon RX 9070 XT (16GB) · ← full hardware catalog · prices verified at source, may drift