yolovino (@yol1) 在 qwen3.8-flash 24GB显存 本地部署教程及测试 中发帖

推理引擎strata 
 [image] 
 [image] 
部署教程如下 
download file and Extract 
conda create -n strata-build -c conda-forge python=3.12 cmake ninja -y 
conda activate strata-build

cd ~/Strata-main
./setup.sh


根据本地硬件实际情况选择,我这里全拉满 

 [image] 

追求质量选择原版+4(ipq3_s) 

 [image] 

选择64k 

[image] 

复杂推理选8bit 


如遇代理问题可手动下载 

Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00001-of-00002.gguf 
Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-00002...
 
 
Back to Top