FastFrames S

Released
2026-11-17
Last refreshed
2026-11-18
Status
Researched today
Open weightsCommercial use: not permittedMultimodal

FastFrames S is a released general LLM work model with open-weight; evaluate it while provider pricing coverage matures.

Apple Machine Learning Research releases · 2 in the last 12 monthsChangelog →
Specifications
Released
2026-11-17
Parameters
1.3B
Specialization
video-generation
Openness
Open weights
Weights
Available
Code
Unknown
Created by

On-device AI prioritizes user privacy

Cupertino, California, United States
Founded 1976
Website
Pricing

No tracked provider pricing is available yet.

About

FastFrames S is Apple’s autoregressive video diffusion model for interactive generation. It generates 480p video in two diffusion steps using optimized components for decoding and context updates. The small variant has 1.3B parameters and builds on Causal Forcing++ and Wan2.1. Its downloadable weights are licensed only for noncommercial research.

Providers

No active provider routes are tracked for this model yet.

Capabilities

VisionMultimodal

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.