Hugging Face's logo

FastVideo
/
FastH3-Omni-MLX

MLX
MiniMax H3
apple-silicon
fastvideo
fasth3-omni
benchmark
Model card Files
xet
 Community

FastH3 Omni on Apple Silicon (MLX) — build + benchmark kit

FastH3 Omni (reference-conditioned video + audio) runs natively on Apple Silicon through FastVideo's MLX runtime (hao-ai-lab/FastVideo#2000).

This repository holds the kit, not the weights:

  • bench/prepare_model_dir.sh builds the MLX model directory from the public releases (FastVideo/FastVideo-FastH3-Omni-8-Step-V1, FastVideo/FastH3-Omni-NVFP4-QAD, FastVideo/FastH3-NVFP4-VAE-Decoder, lightx2v/LightVAE) at pinned revisions: INT6 (default), INT8 or BF16 transformer, NVFP4 text-encoder cache, FastH3 36L/8L decoders and the LightVAE Lite H3 reference encoder. It verifies every file against SHA-256.
  • bench/run_matrix.py runs the FastH3 Omni reference workloads and writes a latency table. See bench/README.md.

Licenses: MiniMax-H3 Community License for the model weights; Qwen3-VL and LightVAE are Apache-2.0 (see bench/licenses/).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for FastVideo/FastH3-Omni-MLX

Base model

MiniMaxAI/MiniMax-H3
Finetuned
FastVideo/FastVideo-FastH3-Omni-8-Step-V1
Finetuned
(7)
this model

Collection including FastVideo/FastH3-Omni-MLX