---
license: other
license_name: minimax-h3-community-license-agreement
license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
base_model: MiniMaxAI/MiniMax-H3
base_model_relation: quantized
library_name: mlx
tags:
- mlx-serve
- text-to-video
- image-text-to-video
- audio-video-generation
---

# MiniMax-H3 FL2VA — MLX-Serve 8-bit

8-bit affine (group size 64) conversion of MiniMax-H3's FL2VA checkpoint for
[mlx-serve](https://github.com/ddalcu/mlx-serve), running natively on Apple
Silicon. Text-to-audio-video: the DiT denoises video and stereo audio jointly
in one packed sequence.

Self-contained: weights, both VAEs and the tokenizer in one directory. Upstream
splits these across `Comfy-Org/MiniMax-H3` (weights, no tokenizer) and
`MiniMaxAI/MiniMax-H3` (tokenizer).

Quantized: the DiT and text-encoder matmul weights. Kept dense: gathered
embedding tables, the checkpoint's fp32 islands (patch projections, output
heads, time embedder) and both VAEs.

Note that quantization here buys FOOTPRINT, not speed — the workload is
compute-bound at roughly 192,000 FLOPs per weight byte.

## Modifications

These are MODIFIED files. The transformer and text encoder are quantized to
8-bit; see MODIFICATIONS.md for the full list. The VAEs and tokenizer are
unmodified copies.

## License

Powered by MiniMax H3. Licensed under the MiniMax H3 Community License
Agreement -- see LICENSE and NOTICE, both included here.

**Territorial restriction.** The Agreement defines the Applicable Territory as
worldwide EXCLUDING the European Union, the United Kingdom, the Republic of
Korea and the United States of America, and Section V.4 prohibits use,
reproduction, modification, distribution and display outside it. Check whether
your jurisdiction permits you to use these files before downloading them.