Video models · ByteDance

Bernini-R A14B (video generation + editing)

Name: Bernini-R A14B (video generation + editing)
Author: ByteDance

Backbone: 14.3B
Native output: 848×480, 81 frames
Default steps: 40
License: apache-2.0
Released: 2026-06

How to run it

Original weights · Hugging Face

Full-precision files from ByteDance, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/ByteDance/Bernini-R (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from ByteDance. The weights themselves download from Hugging Face.

github.com/bytedance/Bernini (opens in a new tab)

git clone https://github.com/bytedance/Bernini

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run Bernini-R A14B (video generation + editing)

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Windows PC, NVIDIA GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

App	Type	Opens it as	Systems	Engine	Start
ComfyUI	Desktop app	Built-in support	macOSWindowsLinux	PyTorch, GGUF via ComfyUI-GGUF	Get ComfyUI
SwarmUI	Desktop app	Built-in support	macOSWindowsLinux	ComfyUI	Get SwarmUI
SD.Next	Desktop app	Built-in support	macOSWindowsLinux	PyTorch	Get SD.Next
Stability Matrix	Desktop app	Built-in support	macOSWindowsLinux	installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus	Get Stability Matrix

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision	Everything on GPU	Text encoder offloaded	Sequential offload	Download
`FP16`	46.0 GB	34.6 GB	15.7 GB	Original weights (opens in a new tab)
`FP8`	26.0 GB	20.3 GB	10.7 GB	Original weights (opens in a new tab)

Components

Backbone: 14.29B
VAE: 0.127B
umT5-XXL: 5.7B

Best hardware for Bernini-R A14B (video generation + editing)

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B580 (launch price $249) at FP8.

Quality	Hardware	Quant	Memory	Speed	Runs
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`FP8`	26.0 GB / 32.0 GB	9.0 min	Runs well
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`FP16`	46.0 GB / 96.0 GB	8.8 min	Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`FP8`	20.3 GB / 24.0 GB	11.3 min	Runs wellencoder in RAM
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 80GB SXM	`FP16`	46.0 GB / 80.0 GB	8.4 min	Runs well
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H800 80GB SXM	`FP16`	46.0 GB / 80.0 GB	8.4 min	Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA A100 40GB	`FP8`	26.0 GB / 40.0 GB	11.3 min	Runs well
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 80GB PCIe	`FP16`	46.0 GB / 80.0 GB	10.2 min	Runs well
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GH200 Grace Hopper (96 GB GPU)	`FP16`	46.0 GB / 96.0 GB	8.4 min	Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA L40S	`FP8`	26.0 GB / 48.0 GB	10.0 min	Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX 6000 Ada Generation	`FP8`	26.0 GB / 48.0 GB	10.0 min	Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.