llamaperf

Qwen3.8 27B

on 4× NVIDIA RTX 5090 · 4,096 ctx

NVIDIA hardware
Sep 7, 2026
VRAM reported
32 GB

Summary

User compares GGUFs of Qwen3.8-27B on 4x RTX 5090. Quants mentioned are Q8_0, IQ1_M, Q3_K_M, AD-IQ3_S and Q6_K, with KLD values reported. No tokens per second are given.