ComfyUI Node: Qwen Thinking Loader (Merged or Sharded)
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
Qwen/Thinking
Inputs
model_folder
- No model folders found in models/qwen/
device
- cuda
- cpu
dtype
- bf16
- fp16
- fp32
- auto
compile_model BOOLEAN
use_multi_gpu BOOLEAN
keep_loaded BOOLEAN
Outputs
QWEN_THINKING_MODEL
QWEN_TOKENIZER
QWEN_THINKING_MODEL
Extension: Qwen-llm-loader
Local Qwen loader and prompt refiner for ComfyUI
Authored by capitan01R
Looking for a different node?
More nodes in Qwen-llm-loader
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.