llamaperf
Submit

Qwen3.8 27B

on Unknown GPU · llama.cpp

Tone: positive
Sep 7, 2026
Share
Throughput
19.2 t/s gen
Quant
Q2_XXS (GGUF)
VRAM reported
12 GB

Summary

User reports Qwen3.8 27B at 19.2 t/s with a Q2_XXS quant and 10.9 t/s with a Q4_KS quant on a 12 GB GPU. Setup is llama.cpp, with the configuration tuned by GPT-5.6.
View source ↗