H3-Tiny-17B-Pruned-Ref2VA vs H3-Tiny-17B-FewStep-Ref2VA-v0.1
On paper these are very alike. Compare a few outputs of your own.
H3-Tiny
H3-Tiny-17B-Pruned-Ref2VA
- Arena—
- From—
- Max length—
H3-Tiny
H3-Tiny-17B-FewStep-Ref2VA-v0.1
- Arena—
- From—
- Max length—
Add a model
Make it a three-way comparison.
Where they differ
Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.
- NewestSame release dateH3-Tiny-17B-Pruned-Ref2VA Nov 19, 2026 · H3-Tiny-17B-FewStep-Ref2VA-v0.1 Nov 19, 2026
- Widest inputsSame inputsH3-Tiny-17B-Pruned-Ref2VA: Text prompts, Reference images · H3-Tiny-17B-FewStep-Ref2VA-v0.1: Text prompts, Reference images
- Native audioBoth generate soundGenerates an audio track with the video: H3-Tiny-17B-Pruned-Ref2VA yes · H3-Tiny-17B-FewStep-Ref2VA-v0.1 yes
- Image to videoBoth animate imagesStarts from an uploaded image: H3-Tiny-17B-Pruned-Ref2VA yes · H3-Tiny-17B-FewStep-Ref2VA-v0.1 yes
- Self-hostingAll open weightsDownloadable weights (MiniMax H3 Community License)
- Most API hostsSame reachH3-Tiny-17B-Pruned-Ref2VA: 0 · H3-Tiny-17B-FewStep-Ref2VA-v0.1: 0
Every spec in one table
Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Task | Audiovisual generation | Audiovisual generation |
| Published capabilities | Generates video and synchronized sound from reference imagery using a pruned MiniMax H3 transformer. | Generates video and synchronized sound from reference imagery using a pruned MiniMax H3 transformer. |
| Model size | 17.07B transformer parameters | 17.08B transformer parameters |
| Access | Downloadable transformer checkpoint for the H3 pipeline | Downloadable transformer checkpoint for the H3 pipeline |
| Operating limits | 50 steps | Six steps by default |
| Sources | Model weights | Model weights |
| Output | ||
| Produces | Video with sound | Video with sound |
| Sound | Always generated | Always generated |
| Inputs | ||
| Text prompts | Yes | Yes |
| Start image (image to video) | Yes | Yes |
| Video input | No | No |
| Audio input | No | No |
| Access | ||
| Weights | OpenMiniMax H3 Community License | OpenMiniMax H3 Community License |
| Released | Nov 19, 2026 | Nov 19, 2026 |
Which should you choose?
Which is better, H3-Tiny-17B-Pruned-Ref2VA or H3-Tiny-17B-FewStep-Ref2VA-v0.1?
Neither model has enough arena votes for a reliable quality score yet, so this page compares specs only. Run the same three or four prompts through each and judge the results.
What is the difference between H3-Tiny-17B-Pruned-Ref2VA and H3-Tiny-17B-FewStep-Ref2VA-v0.1?
H3-Tiny-17B-Pruned-Ref2VA is a video model from H3-Tiny (Nov 19, 2026), taking text prompts and reference images and producing video with sound. H3-Tiny-17B-FewStep-Ref2VA-v0.1 is a video model from H3-Tiny (Nov 19, 2026), taking text prompts and reference images and producing video with sound.
Which is newer?
H3-Tiny-17B-Pruned-Ref2VA Nov 19, 2026; H3-Tiny-17B-FewStep-Ref2VA-v0.1 Nov 19, 2026.
Which generates video with sound?
Generates an audio track with the video: H3-Tiny-17B-Pruned-Ref2VA yes; H3-Tiny-17B-FewStep-Ref2VA-v0.1 yes.
Can I run any of these on my own hardware?
All open weights. Downloadable weights (MiniMax H3 Community License).