llamaperf

Raon-1 29B (4B active) mini-preview

on NVIDIA RTX 5070 Ti · ik_llama.cpp

Tone: positiveNVIDIA hardware
Oct 29, 2026
Throughput
232.0 t/s gen
Quant
IQ3_KS (GGUF)
System RAM
48 GB
VRAM reported
16 GB

Summary

User reports Raon-1-mini-preview at 232 tok/s on an RTX 5070 Ti 16GB, up from 50 tok/s. Setup is ik_llama.cpp with an IQ3_KS GGUF, weights streamed from system RAM on a machine with a Ryzen 5 5600X and 48GB DDR4. The 232 tok/s is the combined result of stacked optimizations, with weights streaming at about 2/3 of the card's peak bandwidth.