ComfyUI Node: Ollama Unload (free VRAM)
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
Ollama
Inputs
url STRING
model STRING
wait BOOLEAN
timeout INT
free_comfy_vram BOOLEAN
passthrough *
Outputs
*
STRING
Extension: ComfyUI_OllamaUnload
Unload one or all Ollama models mid-workflow to free VRAM before image sampling. Wire your prompt through the passthrough socket so the node runs before the sampler. Node name: Ollama Unload (free VRAM). Located under Add Node > Ollama.
Authored by bradsec
Looking for a different node?
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.