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

Install ComfyUI-BerniniR and ComfyUI-GGUF.
Put the .gguf files in ComfyUI/models/unet/. You also need the Wan VAE (wan_2.1_vae.safetensors) and the UMT5 text encoder (umt5_xxl_fp8_e4m3fn_scaled.safetensors).
t2v / t2i (source_id=0 is identical to stock Wan 2.2): one UnetLoaderGGUF → your sampler.
Editing (i2i / v2v), both experts: load each GGUF with UnetLoaderGGUF, send each through BerniniR · Apply Patches, then into BerniniR · Guider (model = high, model_low = low). The guider switches expert by timestep (t=875) and runs the APG guidance. Ready-made graph: workflows/ui/bernini_i2i_gguf_dual.json in the node repo.

License: Apache-2.0 (same as the base model).

neuregex/Bernini-R-GGUF

Bernini-R — GGUF (high & low noise experts)

Files

Usage in ComfyUI

neuregex/
Bernini-R-GGUF