▲ local intelligence

can it run

Can the NVIDIA GeForce GTX 1650 run kokoro 82M?

FULL

2.3 GB needed of 4 GB usable — headroom for context

4GB · Turing · model file 0.3GB · 82M

~200–310 tok/s

computed roofline: 128.1 GB/s × 0.48–0.72 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)

→ gtx-1650-super — the next step up from NVIDIA GeForce GTX 1650

→ every model the NVIDIA GeForce GTX 1650 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 GTX 1650 · fit = weights + 4k KV vs usable memory