Kimi K2.5 1000B (32B active)
on NVIDIA RTX 5090 · llama.cpp
Summary
User reports Kimi K2.5 IQ3_M at 471.40 t/s prompt processing on an RTX 5090, with 80 GB offloaded and the card at 500W.
User also tested GLM 5.1 IQ4_NL at 574.98 t/s prompt processing with 70 GB offloaded.
The user compares these results with an RTX 6000 PRO MaxQ that has a shunt mod.