xiaoxiao150 /
vram-switcher
GPU coordination for local AI companions on AstrBot / DeepSeek Harness: persona LLM, IndexTTS voice and ComfyUI selfies take turns on one 12 GB card. No proxy.
Updated 8 min ago
+7 stars gained this week
Stars gained each day, last 30 days
Oct 9Oct 24
This week Before
In short
Windows-only in practice, needs an NVIDIA card with about 12 GB, and works with llama.cpp, IndexTTS and ComfyUI; no proxy or client change, and the switch order lives in one JSON profile.
Summary written by AI from the repository’s description and README.
xiaoxiao150 / vram-switcher
View on GitHub(opens in new tab)