llamaperf

Ornith1.5 35B (3B active)

on Unknown GPU · Ollama

Tone: positive
Sep 9, 2026
Throughput
64.0 t/s gen

Summary

User reports Ornith1.5 35B A3B at 64 t/s after fixing the MTP head, up from 60 t/s, and 33% faster wall clock. The model is a splice of a trained MTP head onto an APEX requant. The user mentions running on a PC with a hackRF receiver and a 5 watt quansheng portable.