ModelListedExternal

Bernini R GGUF

💻 Code / ComfyUI nodes > 💬 Discord — updates, roadmaps, projects, or just to chat > 🧬 Bernini-R > Wan2.2-T2V-A14B

Sourcehuggingface.co/neuregex/Bernini-R-GGUF/tree/8344f64a3a95447f00f297c0c0b7e2ec5922a07c

KindOtherBase modelByteDance/Bernini-RVersionRevision 8344f64Bgrade

Model source

Kind: Other
File size: 9.00–14.4 GB
Base model: ByteDance/Bernini-R
Version: vRevision 8344f64
Updated: Sep 26, 2026
Downloads: 26.9K
Source: Hugging Face

Source description

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

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).

Sources

1 source

Hugging FacePrimaryVersion 8344f64a3a95447f00f297c0c0b7e2ec5922a07c

huggingface.co/neuregex/Bernini-R-GGUF/tree/8344f64a3a95447f00f297c0c0b7e2ec5922a07c

Verified Aug 15

Model artifacts

6 artifacts

bernini_r_high_noise_14B-Q4_K_M.gguf

gguf · 9.00 GB · SHA-256 c298987ba523…3f96 · Hugging Face

Download

bernini_r_high_noise_14B-Q5_K_M.gguf

gguf · 10.1 GB · SHA-256 73271a6fb579…27ce · Hugging Face

Download

bernini_r_high_noise_14B-Q8_0.gguf

gguf · 14.4 GB · SHA-256 dda4a1a90bab…68e0 · Hugging Face

Download

bernini_r_low_noise_14B-Q4_K_M.gguf

gguf · 9.00 GB · SHA-256 1cbcc61158fc…464a · Hugging Face

Download

bernini_r_low_noise_14B-Q5_K_M.gguf

gguf · 10.1 GB · SHA-256 db5f5294b04a…c041 · Hugging Face

Download

bernini_r_low_noise_14B-Q8_0.gguf

gguf · 14.4 GB · SHA-256 2c8aeeea847b…57df · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeAug 15huggingface.co/neuregex/Bernini-R-GGUF

--- license: apache-2.0 base_model: ByteDance/Bernini-R pipeline_tag: text-to-video library_name: gguf tags: - gguf - wan2.2 - comfyui - bernini-r - text-to-video - image-editing - video-editing --- # Bernini-R — GGUF (high & low noise experts) **[💻 Code / ComfyUI nodes](https://github.com/neuregex/ComfyUI-BerniniR)** > **[💬 Discord — updates, roadmaps, projects, or just to chat](https://discord.gg/HxfP9TnctJ)** > **[🧬 Bernini-R](https://huggingface.co/ByteDance/Bernini-R)** > **[Wan2.2-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)** GGUF quantizations of **[ByteDance/Bernini-R](https://huggingface.co/ByteDance/Bernini-R)** (= Wan2.2-T2V-A14B + source-id RoPE + multi-condition APG guidance), for use in ComfyUI with **[ComfyUI-BerniniR](https://github.com/neuregex/ComfyUI-BerniniR)** + [`city96/ComfyUI-GGUF`](https://github.com/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](https://github.com/neuregex/ComfyUI-BerniniR)** and **[ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF)**. 2. 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`). 3. **t2v / t2i** (`source_id=0` is identical to stock Wan 2.2): one `UnetLoaderGGUF` → your sampler. 4. **Editing (i2i / v2v), both experts:** load each GGUF with `UnetLoaderGGUF`, send each through **BerniniR · Apply Patches**, then into **BerniniR · Guider** (`model` = high, `model_l...

NoteAug 15huggingface.co/neuregex/Bernini-R-GGUF

Source context: 26894 downloads · 30 likes · Pipeline text-to-video · Library gguf · Repo neuregex/Bernini-R-GGUF