Ornith1.5 9B
on NVIDIA RTX 4060 · llama.cpp
Oct 12, 2026
Summary
User reports Ornith 1.5 9B at ~15 tok/s generation and ~200 tok/s prompt processing on an 8 GB RTX 4060.
Setup is llama.cpp with Q8_0 KV cache and MTP speculative decoding via a draft model, flash attention on.
Without MTP the user gets double these numbers, and reports a 0.95 draft acceptance rate with a mean accepted length of 2.27. The user also notes memory bandwidth and GPU utilisation are about half with MTP enabled.