ComfyUI Node: (Deno) Local LLM Loader

Authored by Deno2026

Created

Updated

116 stars

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

Deno/LLM

Inputs

provider
  • Ollama
  • LM Studio
  • llama.cpp
  • vLLM
  • Custom
ollama_model
lm_studio_model
custom_server_url STRING
custom_model STRING
system_prompt STRING
thinking BOOLEAN
seed INT
seed_mode
  • fixed
  • increment
  • decrement
  • randomize
model_memory
  • Unload after run
  • Keep for minutes
  • Keep loaded
keep_minutes INT
comfy_vram_policy
  • Auto: unload only before first LLM call
  • Always unload before each LLM call
  • Never unload before LLM call
prompt STRING
image IMAGE

Outputs

STRING

Extension: Deno Custom Nodes

Korean-friendly practical custom nodes for ComfyUI

Authored by Deno2026

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.

Learn more