ComfyUI Node: MD: LLM VRAM Manager
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
MD_Nodes/Utility
Inputs
action
- None (Do Nothing)
- Unload Ollama Models (API)
- Unload llama-swap Models (API)
- Unload LM Studio Model (SDK) [DISABLED]
- Unload ALL (Ollama/llama-swap/LM Studio) [LM Studio DISABLED]
- ---FORCE STOP (USE WITH CAUTION)---
- Stop Ollama Process (Force)
- Stop LM Studio Process (Force)
- Stop BOTH Ollama & LM Studio (Force)
trigger BOOLEAN
pass_through *
seed_in INT
image_in IMAGE
latent_in LATENT
debug_mode
- 0 - Silent
- 1 - Info
Outputs
*
STRING
INT
IMAGE
LATENT
Extension: MD Nodes
A wild collection of custom nodes for ComfyUI including noise schedulers, samplers, audio preview, latent visualizers, and more β built for maximal creative chaos.
Authored by MDMAchine
Looking for a different node?
More nodes in MD Nodes
Other MD_Nodes/Utility nodes
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.