local intelligence

can it run

Can the GTX 1080 Ti (11GB, used) run llava 13B?

TIGHT

Yes, but close to the edge. 11GB against a 10GB working set: it runs, with little room for long context windows or other processes.

~17–30 tok/s

weights 8GB + KV cache 3.12GB at 4k context vs ~11GB usable → tight. 11.1 of 11 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

computed roofline: 484 GB/s × 0.28–0.50 efficiency window / 8.0GB (Q4_K_M) — bands, never points.

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

Specs

model file8.0GB (GGUF Q4_K_M)
minimum memory10GB working set
this machine11GB GDDR5X, 484 GB/s
params13B
licenseapache-2.0
price$275

Run it

model files: hugging face ↗

easy run: ollama pull llava:13b

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

Alternatives

Tesla P100 (16GB, used) — cheapest machine that runs it ($135)

every model the GTX 1080 Ti (11GB, used) can run — full list

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

Buy

eBay (used) ↗ · Amazon ↗

2026-09-17 · ← all models on the GTX 1080 Ti (11GB, used) · ← full hardware catalog · prices verified at source, may drift