llamaperf

Qwen3.8 27B

on NVIDIA RTX 3090

NVIDIA hardware
Sep 7, 2026
Throughput
55.0 t/s gen
VRAM reported
24 GB

Summary

User reports Qwen3.8-27B at 55 tok/s on an RTX 3090. Setup is the IQ4_XS quant. The user also mentions GLM-5.3 pricing and intelligence, DeepSeek V4 Flash, and Strix Halo hardware, but does not run them.