llamaperf
Submit

Qwen3.6 35B (3B active)

on CMP170HX · NInfer · 262,144 ctx

Tone: positive
Aug 28, 2026
Share
Throughput
210.0 t/s gen · 4000.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
KV cache
Q8
MTP (Multi-Token Prediction)
on

Use cases

agenticvision

Summary

User reports a forked Ninfer on a CMP 170HX roughly doubles performance versus llama.cpp on Qwen3.6-35B-A3B. The setup is used for a Home Assistant voice assistant.
View source ↗