Instructions to use antocorr/MiniMax-H3-FL2VA-MLX-Serve-2bit-text-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use antocorr/MiniMax-H3-FL2VA-MLX-Serve-2bit-text-encoder with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiniMax-H3-FL2VA-MLX-Serve-2bit-text-encoder antocorr/MiniMax-H3-FL2VA-MLX-Serve-2bit-text-encoder
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
MiniMax-H3 FL2VA โ MLX-Serve, 2-bit text encoder / 4-bit DiT
Variant of the 4-bit MLX-Serve conversion of MiniMax-H3's FL2VA checkpoint: only the Qwen3-VL text encoder is quantized to MLX affine 2-bit (group size 64); the DiT stays affine 4-bit and the VAEs, tokenizer and config are byte-for-byte identical to the 4-bit release. Runs natively on Apple Silicon via mlx-serve. Text-to-audio-video: the DiT denoises video and stereo audio jointly in one packed sequence.
| Component | File | Quantization |
|---|---|---|
| Qwen3-VL text encoder | text_encoder.safetensors |
affine 2-bit, g64 (file metadata: affine 2-bit g64) |
| DiT (MiniMax-H3) | transformer.safetensors |
affine 4-bit, g64 |
| Video VAE | video_vae.safetensors |
dense f16, unmodified |
| Audio VAE | audio_vae.safetensors |
dense f32, unmodified |
| Tokenizer | tokenizer.json etc. |
unmodified |
How it loads: mlx-serve's MfLinear (shared by the H3 and MageFlow backends)
derives (bits, group_size) per tensor from the packed geometry โ bits = 32ยทw_cols/in_features, group_size = in_features/scales_cols โ so each file
is self-describing and no config change is needed. Every quantized tensor in
text_encoder.safetensors solves to (2, 64); the DiT solves to (4, 64). The
quantization block in config.json is advisory for this backend (reporting
only) and still describes the DiT.
Same staged residency as the 4-bit release: the text encoder is loaded, run and freed before the DiT loads. The 2-bit encoder packs ~9.6 GB on disk vs ~15.8 GB at 4-bit.
Quality note: 2-bit affine is lossier than 4-bit by design. The text conditioning (prompt adherence) is where you may notice it; the DiT, VAEs and tokenizer are untouched, so frame/audio quality is otherwise the 4-bit release's.
Usage
Serve it with mlx-serve (a 32 GB Mac needs --skip-mem-preflight):
/Applications/MLX Core.app/Contents/MacOS/mlx-serve \
--model /path/to/MiniMax-H3-FL2VA-MLX-Serve-2bit-text-encoder \
--serve --host 127.0.0.1 --port 11235 --skip-mem-preflight
Then POST /v1/video/generations with {"prompt", "width", "height", "num_frames", "steps", "seed"} โ the response is base64 rgb8 frames plus
pcm_s16le audio on the standard native wire format. A ready-to-run wrapper
script is provided in the source directory of this conversion (h3gen.sh),
with --te=2bit|4bit to switch between this variant and the original 4-bit
release.
Modifications
These are MODIFIED files. The text encoder is quantized to 2-bit and the DiT to 4-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.
- Downloads last month
- -
Quantized
Model tree for antocorr/MiniMax-H3-FL2VA-MLX-Serve-2bit-text-encoder
Base model
MiniMaxAI/MiniMax-H3