This is a compact, native-MLX FL2VA inference package for
mere.run. It generates synchronized
24 fps video and 32 kHz stereo audio from text, a first frame, or directed
first/last frames on Apple Silicon.
License and territory notice
These model files are governed by the included MiniMax-H3 Community License
Agreement, not the mere.run source-code license. The license excludes use,
distribution, and display in the United States, European Union, United
Kingdom, and Republic of Korea and imposes downstream notice, modification,
safety, and distribution obligations. Read LICENSE,
NOTICE, and MODIFICATIONS.md before download,
use, or redistribution.
By downloading, accessing, reproducing, or using these files, you acknowledge
and accept the MiniMax-H3 Community License Agreement and agree to comply with
it. The agreement does not authorize use, distribution, or display in the
United States, European Union, United Kingdom, or Republic of Korea.
Provenance
Every tensor input came directly from the public official checkpoint:
No converted or quantized third-party weights were used. The release was built
with scripts/model-conversion/convert_minimax_h3_official_mlx.py from the
mere.run repository in a declared Canadian conversion location. The converter
verifies all 144.04 GB of official source files, checks the exact upstream
license bytes, and requires MLX's CUDA Q4/Q8 packing to match byte-level
fixtures captured on Apple Silicon before conversion.
SHA256SUMS: SHA-256 for every distributed runtime and legal
file.
Numeric transforms
52 fused transformer/refiner QKV matrices: reordered from MiniMax's released
per-head [q,k,v] row interleave into the official reference model's global
[all-q; all-k; all-v] layout required by the native runtime;
208 active transformer/refiner core linears: official BF16 directly to MLX
affine Q4, group size 64 after the QKV layout transform;
precision-sensitive transformer projections, normalization, and outputs:
retained at released BF16/F32 precision;
exact 50-layer Qwen3-VL conditioner used by H3: 439 eligible linears from
official BF16 directly to MLX affine Q8, group size 64;
AdaLN cache: evaluated from the original official BF16/F32 projections over
mere.run's released 31-point schedule before the cache-covered 13B-parameter
inference branch was omitted;
video VAE: official FP32 tensors cast directly to FP16;
audio VAE: official FP32 weight-normalization pairs folded algebraically into
equivalent plain convolution weights.
No weights were retrained, distilled, merged, or used as input from another
quantized repository.
Use with mere.run
bash
1mere.run model pull video-minimax-h3-fl2va-mlx --accept-model-license
2mere.run video generate \3"a jeweled hummingbird hovering beside a red orchid, cinematic natural light"\4 --model video-minimax-h3-fl2va-mlx \5 --width 512\6 --height 512\7 --num-frames 56\8 --seed 314159\9 --output hummingbird.mp4
The managed package already contains its source-bound AdaLN cache; no
post-download model optimize pass is required. Inference runs locally through
native Swift/MLX. Python and CUDA are release-conversion tools only.
Validation
The complete 14-file managed bundle passed the fail-closed validator at
46,250,104,566 bytes. Anonymous Hub verification then matched the exact remote
file set, public/ungated state, every LFS SHA-256 and size, every small-file
hash, and the first and last 1 MiB of each large tensor.
A full-schedule generation was run locally on an Apple M4 Max with 128 GB of
unified memory using the optimized arm64 release executable (SHA-256
042c25e023dddb71bb9fa44db0cca505dc4fe2115bcb17fd86a81953cebe4614):
