https://github.com/KLL535/ComfyUI Simple Qwen3 VL gguf After compilation is finished, the llama cpp python folder must not be deleted. There is no need to compile it manually anymore. You can use JamePeng’s precompiled WHL package, as long as the CUDA version matches exactly. https://github.com/1038lab/ComfyUI QwenVL https://github.com/JamePeng/llama cpp python https://developer.nvidia.com/cuda toolkit archive Gemma 4 requires llama‑cpp‑python ≥ 0.3.35 ComfyUI\custom nodes\ComfyUI Simple Qwen3 VL gguf\system prompts user.json
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy