llamaperf

Qwen3.8 27B

on 2× NVIDIA RTX 3090

Tone: positiveNVIDIA hardware
Sep 7, 2026
Throughput
40.0 t/s gen
Quant
AWQ-INT4
KV cache
FP8
VRAM reported
24 GB

Use cases

creative-writing

Summary

User reports Qwen3.8 27B at about 40 t/s for SVG generation on 2x RTX 3090. Setup is the cyankiwi/Qwen3.8-27B-AWQ-INT4 model with TP2 and an FP8 KV cache. Speed started near 60 t/s and dropped to the 20s after the user removed a power limit mid-generation. The run took 20 minutes, 12 of them thinking, and the user was impressed with the result.