ZMIME
Video model comparison · 2 models · Updated Nov 21, 2026

H3-Tiny-17B-Pruned-FL2VA vs H3-Tiny-17B-Pruned-Ref2VA

Newest: H3-Tiny-17B-Pruned-FL2VA. Not enough arena votes yet for a quality score, so this is a spec comparison.

  1. H3-Tiny

    H3-Tiny-17B-Pruned-FL2VA

    Released Nov 20, 2026

    • Text to video
    • Image to video
    • Native audio
    • Arena—
    • From—
    • Max length—
  2. H3-Tiny

    H3-Tiny-17B-Pruned-Ref2VA

    Released Nov 19, 2026

    • Text to video
    • Image to video
    • Native audio
    • Arena—
    • From—
    • Max length—
  3. Add a model

    Make it a three-way comparison.

01 — At a glance

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.

  • NewestH3-Tiny-17B-Pruned-FL2VAH3-Tiny-17B-Pruned-FL2VA Nov 20, 2026 · H3-Tiny-17B-Pruned-Ref2VA Nov 19, 2026
  • Widest inputsSame inputsH3-Tiny-17B-Pruned-FL2VA: Text prompts, Reference images · H3-Tiny-17B-Pruned-Ref2VA: Text prompts, Reference images
  • Native audioBoth generate soundGenerates an audio track with the video: H3-Tiny-17B-Pruned-FL2VA yes · H3-Tiny-17B-Pruned-Ref2VA yes
  • Image to videoBoth animate imagesStarts from an uploaded image: H3-Tiny-17B-Pruned-FL2VA yes · H3-Tiny-17B-Pruned-Ref2VA yes
  • Self-hostingAll open weightsDownloadable weights (MiniMax H3 Community License)
  • Most API hostsSame reachH3-Tiny-17B-Pruned-FL2VA: 0 · H3-Tiny-17B-Pruned-Ref2VA: 0
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

H3-Tiny-17B-Pruned-FL2VA vs H3-Tiny-17B-Pruned-Ref2VA specifications side by side
SpecificationH3-Tiny-17B-Pruned-FL2VAH3-TinyH3-Tiny-17B-Pruned-Ref2VAH3-Tiny
TaskAudiovisual generationAudiovisual generation
Published capabilitiesGenerates synchronized video and audio from a prompt or from first and last frames.Generates video and synchronized sound from reference imagery using a pruned MiniMax H3 transformer.
Model size17.07B transformer parameters17.07B transformer parameters
AccessDownloadable transformer checkpoint for the H3 pipelineDownloadable transformer checkpoint for the H3 pipeline
Operating limits50 steps50 steps
SourcesModel weightsModel weights
Output
ProducesVideo with soundVideo with sound
SoundAlways generatedAlways generated
Inputs
Text promptsYesYes
Start image (image to video)YesYes
Video inputNoNo
Audio inputNoNo
Access
WeightsOpenMiniMax H3 Community LicenseOpenMiniMax H3 Community License
ReleasedNov 20, 2026Nov 19, 2026
03 — Questions

Which should you choose?

Which is better, H3-Tiny-17B-Pruned-FL2VA or H3-Tiny-17B-Pruned-Ref2VA?

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-FL2VA and H3-Tiny-17B-Pruned-Ref2VA?

H3-Tiny-17B-Pruned-FL2VA is a video model from H3-Tiny (Nov 20, 2026), taking text prompts and reference images and producing video with sound. 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.

Which is newer?

H3-Tiny-17B-Pruned-FL2VA Nov 20, 2026; H3-Tiny-17B-Pruned-Ref2VA Nov 19, 2026.

Which generates video with sound?

Generates an audio track with the video: H3-Tiny-17B-Pruned-FL2VA yes; H3-Tiny-17B-Pruned-Ref2VA yes.

Can I run any of these on my own hardware?

All open weights. Downloadable weights (MiniMax H3 Community License).