local intelligence

can it run

Can the RTX 2080 / 2080 Super (8GB, used) run WHISPER large-v3?

TIGHT

Yes, but close to the edge. 8GB against a 8GB working set: it runs, with little room for long context windows or other processes.

~35–52 tok/s

weights 6.2GB + KV cache 2GB at 4k context vs ~8GB usable → tight. 8.2 of 8 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context

computed roofline: 448 GB/s × 0.48–0.72 efficiency window / 6.2GB (Q4_K_M) — bands, never points.

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

Specs

model file6.2GB (GGUF Q4_K_M)
minimum memory8GB working set
this machine8GB GDDR6, 448-496 GB/s
paramslarge-v3
licenseapache-2.0
price$305

Run it

model files: hugging face ↗

easy run: no stock runtime yet

Alternatives

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

every model the RTX 2080 / 2080 Super (8GB, used) can run — full list

rtx-3080-10gb — the next step up from this machine's GPU

Buy

eBay (used) ↗ · Amazon ↗

2026-09-17 · ← all models on the RTX 2080 / 2080 Super (8GB, used) · ← full hardware catalog · prices verified at source, may drift