Bernini R — GGUF (high & low noise experts) 💻 Code / ComfyUI nodes 💬 Discord — updates, roadmaps, projects, or just to chat 🧬 Bernini R Wan2.2 T2V A14B GGUF quantizations of ByteDance/Bernini R (= Wan2.2 T2V A14B + source id RoPE + multi condition APG guidance), for use in ComfyUI with ComfyUI BerniniR + city96/ComfyUI GGUF . Bernini R is a dual expert model (Wan 2.2): a high noise expert sets the composition and a low noise expert refines detail. Both are quantized here. GGUF carries no fp8 tensors, so the two experts coexist in 24 GB VRAM without the offload crash the fp8 build hits. Files File Expert Quant Size bernini r high noise 14B Q4 K M.gguf high noise Q4 K M 9.66 GB bernini r high noise 14B Q5 K M.gguf high noise Q5 K M 10.8 GB bernini r high noise 14B Q8 0.gguf high noise Q8 0 15.4 GB bernini r low noise 14B Q4 K M.gguf low noise Q4 K M 9.66 GB bernini r low noise 14B Q5 K M.gguf low noise Q5 K M 10.8 GB bernini r low noise 14B Q8 0.gguf low noise Q8 0 15.4 GB Q5 K M is the recommended balance; Q8 0 for best quality, Q4 K M for the lowest VRAM. Usage in ComfyUI 1. Install ComfyUI BerniniR and ComfyUI GGUF . 2. Put the .gguf files in ComfyUI/models/unet/ . You also nee…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy