JunhaoZhuang · First MLX build 5 Oct 2026
FlashVSR-v1.1
MLX
Text apache-2.0
A video to video model from JunhaoZhuang, with 2 MLX builds, from bf16 to fp32.
- Parameters
- — Not published
- Quantisation
- bf16 FlashVSR-v1.1-bf16
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 118 This build, last 30 days
- Task
- Video to video Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/FlashVSR-v1.1-bf16MLX builds
2 on mlx-community| FlashVSR-v1.1-bf16 | bf16 | — | — | 118 |
|---|---|---|---|---|
| FlashVSR-v1.1-fp32 | fp32 | — | — | 30 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.