local intelligence

can it run

Can the Tesla V100 32GB (used) run LLAMA4 Maverick 400B A17B?

NO

No. 32GB of memory can't hold the 307GB working set this model needs. A smaller quant or a bigger machine is required.

~1.7–2.8 tok/s

weights 245GB + KV cache 0.75GB at 4k context vs ~32GB usable → no. 245.8 GB vs 32 GB usable — does not fit

computed roofline: 897 GB/s × 0.46–0.76 efficiency window / 245.0GB (Q4_K_M) — bands, never points.

explore the full catalog90 machines indexed · live prices · what each one can run

Specs

model file245GB (GGUF Q4_K_M)
minimum memory307GB working set
this machine32GB HBM2, 897 GB/s
paramsMaverick 400B A17B
licensellama4 (gated on HF)
price$645

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 Tesla V100 32GB (used) can run — full list

RTX 3090 (24GB, used) — upgrade path machine

Buy

eBay (used) ↗ · Amazon ↗

2026-09-20 · ← all models on the Tesla V100 32GB (used) · ← full hardware catalog · prices verified at source, may drift