llamaperf

Qwen3.8 27B

on 2× NVIDIA RTX 5060 Ti 16GB · NInfer

Tone: positiveNVIDIA hardware
Sep 9, 2026
Throughput
76.7 t/s gen
Quant
NVFP4
MTP (Multi-Token Prediction)
on
VRAM reported
16 GB

Summary

User reports a custom Windows fork of NInfer running TP2 on two RTX 5060 Ti 16GB cards without P2P. Setup uses MTP, with speeds of 35.75 t/s at MTP0, 57.71 t/s at MTP1, 63.15 t/s at MTP2, and 66.79 t/s at MTP3. MTP4 reaches 68.5-68.9 t/s at 512 tokens, 70.6 t/s at 1024 tokens, and 76.65 t/s at 2048 tokens.