▲ local intelligence

can it run

Can the NVIDIA GeForce RTX 3080 12GB run kokoro 82M?

FULL

2.3 GB needed of 12 GB usable — headroom for context

12GB · Ampere · model file 0.3GB · 82M

~1400–2300 tok/s

computed roofline: 912.4 GB/s × 0.46–0.76 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-3090 — the next step up from NVIDIA GeForce RTX 3080 12GB

→ every model the NVIDIA GeForce RTX 3080 12GB 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 3080 12GB · fit = weights + 4k KV vs usable memory