ComfyUI Node: 🖼️ Vision Model Loader (Transformers)
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
🤖 GGUF-VLM/🖼️ Vision Models
Inputs
model
- Huihui-Qwen3-VL-4B-Instruct-abliterated
- Huihui-Qwen3-VL-8B-Instruct-abliterated
quantization
- none
- 4bit
- 8bit
attention
- eager
- sdpa
- flash_attention_2
keep_model_loaded BOOLEAN
min_pixels INT
max_pixels INT
Outputs
TRANSFORMERS_MODEL
Extension: Qwen2.5-VL GGUF Nodes
ComfyUI nodes for running GGUF quantized Qwen2.5-VL models using llama.cpp
Authored by walke2019
Looking for a different node?
Also provided by 1 other extension
- 🤖 Vision Model Loader (Transformers) — ComfyUI-GGUF-FX🤖 GGUF-Fusion/Transformers
More nodes in Qwen2.5-VL GGUF Nodes
- 🖥️ Local Text Model Loader (GGUF)
- 🧹 Memory Manager (GGUF)
- 🖼️ Image/Video Analysis (Transformers)
- 📊 Service Status Check
- 🌐 Remote Text Model Config (Ollama/Nexa/LM Studio)
- 🖼️ Remote Vision Analysis
- 🌐 Remote Vision Model Config (LM Studio/Ollama)
- 🤖 System Prompt Config
- 🤖 Text Generation
- 🖼️ Local Image Analysis (GGUF)
- 🖼️ Local Vision Model Loader (GGUF)
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.