llamaperf

Qwen3.8 27B Huihui-Abliterated

on NVIDIA RTX 3090 · 131,072 ctx

NVIDIA hardware
Sep 9, 2026
Throughput
25.6 t/s gen
Quant
Q4_K_S
KV cache
Q4
System RAM
48 GB
VRAM reported
24 GB

Summary

User reports Huihui Qwen3.8-27B Abliterated Q4_K_S at an average TG of ~25.58 tok/s on an RTX 3090 24GB at 131072 context, in a conversation of 111797 tokens. Setup uses a Q4 KV cache with 23.5/24.0 GB dedicated and 0.6/31.8 GB shared GPU memory, on a Xeon E5-2670 v3 with 48GB DDR4-2133, and each run logs a DTA of 64.2% to 70.8%. Individual runs read 22.02 to 31.94 tok/s. At 196608 context the average TG is 25.80 tok/s with an average DTA of 64.57%.