llamaperf

Qwen3.5 9B

on P106-100

Oct 21, 2026
Throughput
30.0 t/s gen
VRAM reported
6 GB

Summary

User reports a 9B Qwen3.5 model at 30 t/s on a single P106-100 6GB card after extreme undervolting. No engine, quant or context length is stated for the run. Speed dropped to 25 t/s after 4k tokens were generated in one go. User is considering buying 12 of these cards at $20 each and asks whether 70B+ models would hold at least 10 t/s.