Titan Xp

Speed is modeled, not measured: decode is memory-bandwidth bound, so tokens per second is bytes read per token against achievable bandwidth. Mixture-of-experts models carry a wider band because only the routed experts are read each step, and few have been measured publicly.

What AI models can a Titan Xp run?

1448 of 2118 indexed open-weight models fit a Titan Xp at 65,536 context with q8_0 KV cache, the largest being Qwen3-16B-A3B at Q3_K_L. That covers text, vision-language, image, video and speech models.

How much usable memory does a Titan Xp actually have?

Its nameplate is 12 GB, but about 11.16 GiB is available to a model once driver and compositor overhead is accounted for.

Is a Titan Xp fast for local AI?

Its memory bandwidth is 548 GB/s, and that figure — not teraflops — is what governs token generation speed. Capacity decides what you can run; bandwidth decides how fast it runs.