local intelligence

can it run

Can the Tesla P100 (16GB, used) run LLAMA4 Scout 109B A17B?

NO

No. 16GB of memory can't hold the 84GB working set this model needs. A smaller quant or a bigger machine is required.

~1.9–4.2 tok/s

weights 67GB + KV cache 0.75GB at 4k context vs ~16GB usable → no. 67.8 GB vs 16 GB usable — does not fit

computed roofline: 732 GB/s × 0.17–0.38 efficiency window / 67.0GB (Q4_K_M) — bands, never points.

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

Specs

model file67GB (GGUF Q4_K_M)
minimum memory84GB working set
this machine16GB HBM2, 732 GB/s
paramsScout 109B A17B
licensellama4 (gated on HF)
price$135

Run it

model files: hugging face ↗

easy run: ollama pull llama4:scout

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

Alternatives

NIMO AI Mini PC (128GB) — cheapest machine that runs it ($1999)

every model the Tesla P100 (16GB, used) can run — full list

tesla-v100-16gb — the next step up from this machine's GPU

Buy

eBay (used) ↗ · Amazon ↗

2026-09-17 · ← all models on the Tesla P100 (16GB, used) · ← full hardware catalog · prices verified at source, may drift