▲ local intelligence

can it run

Can the NVIDIA GeForce RTX 4080 SUPER run kokoro 82M?

FULL

2.3 GB needed of 16 GB usable — headroom for context

16GB · Ada · model file 0.3GB · 82M

~1200–2000 tok/s

computed roofline: 736 GB/s × 0.50–0.80 efficiency window / 0.3GB (Q4_K_M) — bands, never points.

Run kokoro 82M on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs kokoro 82M fully ($35)

→ rtx-4090 — the next step up from NVIDIA GeForce RTX 4080 SUPER

→ every model the NVIDIA GeForce RTX 4080 SUPER can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the NVIDIA GeForce RTX 4080 SUPER · fit = weights + 4k KV vs usable memory