ComfyUI Node: ThinkingLLM Advanced (GGUF)

Authored by goodguy1963

Created

Updated

13 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

ThinkingLLM

Inputs

model_name
  • Qwen3-VL-4B-Instruct-c_abliterated-v2.Q4_K_M.gguf [~2.4GB]
  • Qwen3-VL-4B-Instruct-c_abliterated-v2.Q5_K_M.gguf [~2.8GB]
  • Qwen3-VL-4B-Instruct-c_abliterated-v2.Q6_K.gguf [~3.2GB]
  • Qwen3-VL-4B-Instruct-c_abliterated-v2.Q8_0.gguf [~4.2GB]
  • Qwen3-VL-4B-Instruct-c_abliterated-v2.f16.gguf [~8GB]
  • Qwen3-VL-8B-Instruct-c_abliterated-v3.Q4_K_M.gguf [~5.3GB]
  • Qwen3-VL-8B-Instruct-c_abliterated-v3.Q5_K_M.gguf [~6.5GB]
  • Qwen3-VL-8B-Instruct-c_abliterated-v3.Q6_K.gguf [~7.5GB]
  • Qwen3-VL-8B-Instruct-c_abliterated-v3.Q8_0.gguf [~9GB]
  • Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf [~16GB]
  • Qwen3.5-27B-Q4_K_M.gguf [~15GB]
  • Qwen3.5-27B-Q5_K_M.gguf [~18GB]
  • Qwen3.5-27B-Q6_K.gguf [~21GB]
  • Qwen3.5-27B-Q8_0.gguf [~27GB]
  • Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-BF16.gguf [~54GB]
  • Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf [~15GB]
  • Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf [~21GB]
  • Qwen3.5-27B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf [~27GB]
  • Qwen3.5-4B-BF16.gguf [~8GB]
  • Qwen3.5-4B-Q4_K_M.gguf [~2.4GB]
  • Qwen3.5-4B-Q6_K.gguf [~3.2GB]
  • Qwen3.5-4B-Q8_0.gguf [~4.2GB]
  • Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf [~8GB]
  • Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf [~2.4GB]
  • Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf [~3.2GB]
  • Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf [~4.2GB]
  • Qwen3.5-9B-BF16.gguf [~18GB]
  • Qwen3.5-9B-Q4_K_M.gguf [~5.3GB]
  • Qwen3.5-9B-Q6_K.gguf [~7.5GB]
  • Qwen3.5-9B-Q8_0.gguf [~9GB]
  • Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf [~18GB]
  • Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf [~5.3GB]
  • Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf [~7.5GB]
  • Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf [~9GB]
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_NL.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf [~11GB]
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf [~20GB]
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf [~31GB]
  • Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf
  • Qwen3VL-4B-Instruct-F16.gguf [~8GB]
  • Qwen3VL-4B-Instruct-Q4_K_M.gguf [~2.4GB]
  • Qwen3VL-4B-Instruct-Q8_0.gguf [~4.2GB]
  • Qwen3VL-4B-Thinking-F16.gguf [~8GB]
  • Qwen3VL-4B-Thinking-Q4_K_M.gguf [~2.4GB]
  • Qwen3VL-4B-Thinking-Q8_0.gguf [~4.2GB]
  • Qwen3VL-8B-Instruct-F16.gguf [~16GB]
  • Qwen3VL-8B-Instruct-Q4_K_M.gguf [~5.3GB]
  • Qwen3VL-8B-Instruct-Q8_0.gguf [~9GB]
  • Qwen3VL-8B-Thinking-F16.gguf [~16GB]
  • Qwen3VL-8B-Thinking-Q4_K_M.gguf [~5.3GB]
  • Qwen3VL-8B-Thinking-Q8_0.gguf [~9GB]
  • gemma-4-12b-it-BF16.gguf [~24GB]
  • gemma-4-12b-it-Q4_K_M.gguf [~7.5GB]
  • gemma-4-12b-it-Q4_K_S.gguf [~7.5GB]
  • gemma-4-12b-it-Q5_K_M.gguf [~9GB]
  • gemma-4-12b-it-Q5_K_S.gguf [~9GB]
  • gemma-4-12b-it-Q6_K.gguf [~11GB]
  • gemma-4-12b-it-Q8_0.gguf [~13GB]
  • gemma-4-12b-it-UD-Q4_K_XL.gguf
  • google_gemma-4-E4B-it-Q4_K_M.gguf [~5.4GB]
  • google_gemma-4-E4B-it-Q5_K_M.gguf [~5.8GB]
  • google_gemma-4-E4B-it-Q6_K.gguf [~6.3GB]
  • google_gemma-4-E4B-it-Q8_0.gguf [~8GB]
  • google_gemma-4-E4B-it-bf16.gguf [~15GB]
device
  • auto
  • cpu
  • mps
preset_prompt
  • 🚫 No preset (image-only)
  • 💬 Custom prompt + image (no preset)
  • 🎦 LTX 2.3 NSFW I2V Scene
  • 🍿 Wan 2.2 NSFW I2V Timeline (3s)
  • 🍿 Wan 2.2 NSFW I2V Timeline (5s)
  • 🎥 Wan 2.2 NSFW I2V Scene (3s)
  • 🎥 Wan 2.2 NSFW I2V Scene (5s)
  • 🎬 Wan 2.2 NSFW I2V Timeline (20s)
  • 📖 Wan 2.2 NSFW I2V Scene (20s)
  • 🍿 Wan 2.2 NSFW T2V Timeline (3s)
  • 🍿 Wan 2.2 NSFW T2V Timeline (5s)
  • 🎥 Wan 2.2 NSFW T2V Scene (3s)
  • 🎥 Wan 2.2 NSFW T2V Scene (5s)
  • 🎬 Wan 2.2 NSFW T2V Timeline (20s)
  • 📖 Wan 2.2 NSFW T2V Scene (20s)
  • 🖼️ Tags
  • 🖼️ Simple Description
  • 🖼️ Detailed Description
  • 🖼️ Ultra Detailed Description
  • 🎬 Cinematic Description
  • 🖼️ Detailed Analysis
  • 📹 Video Summary
custom_prompt STRING
max_tokens INT
temperature FLOAT
top_p FLOAT
repetition_penalty FLOAT
frame_count INT
ctx INT
n_batch INT
gpu_layers INT
image_max_tokens INT
top_k INT
pool_size INT
keep_model_loaded BOOLEAN
seed INT
legacy_seed_mode
  • fixed
  • randomize
  • increment
  • decrement
legacy_unload_after_run BOOLEAN
n_ubatch INT
n_threads INT
n_threads_batch INT
flash_attn BOOLEAN
offload_kqv BOOLEAN
ctx_checkpoints INT
stream_tokens_to_terminal BOOLEAN
enable_thinking BOOLEAN
auto_finalization_retry BOOLEAN
hf_token STRING
image IMAGE
video IMAGE
audio AUDIO
audio_file_path STRING

Outputs

STRING

STRING

Extension: ComfyUI-ThinkingLLM

A multimodal ComfyUI AI node with Qwen3.5, Qwen3-VL, Qwen2.5-VL, Qwen3, and Gemma 4 integrations. Features live thinking in the terminal to see what the LLM is doing in real time.

Authored by goodguy1963

View Nodes

Looking for a different node?

More nodes in ComfyUI-ThinkingLLM

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