llamaperf

Qwen3.8 27B

on NVIDIA RTX 4060 · LM Studio

Tone: negativeNVIDIA hardware
Nov 21, 2026
Throughput
3-4 t/s gen
Quant
IQ3_S (GGUF)
System RAM
16 GB
VRAM reported
8 GB

Summary

User reports Qwen3.8 27B at IQ3_S producing 3-4 tk/s on an RTX 4060 laptop with 16GB DDR5 system RAM. Setup is LM Studio on Pop!_OS, with the model partly offloaded given 8GB VRAM against a 27B model. User asks whether another approach such as polystrata for MoE models could help, and does not want to drop to Q1 just for speed.