运行命令：
yblgt@yblgt-ThinkStation-P710:~/Strata$ ./setup.sh --host 0.0.0.0 --api-key 123456
挂载模型：
http://100.108.44.45:8080/v1
更新命令
cd ~/Strata
./update.sh
Model and engine
Model
qwen3.8-flash-next-iq2_xs
Engine
v0.1.39
Context
131,072 tokens
KV cache
8-bit, all in VRAM
Experts in VRAM
10,713 (14.4 GB)
Speculation
MTP drafts up to 3 tokens, prompt lookup on
Images
off