A third-party team has taken MiniMax's open-weight H3 video model and cut it down to fit on a consumer graphics card, while NVIDIA has already shipped a runtime for it. Here is what the compression actually consists of, what it costs to run, and why the license attached to these weights matters more than the speed numbers suggest.

Three surgical cuts

Video Rebirth states plainly in its repository that it changed the MiniMax-H3 transformer in only three ways.

First, structural pruning plus low-rank factorization. The fl2va partition drops 3 of 50 blocks (blocks 6, 21 and 22) and factors 102 linear layers; the ref2va partition drops only 1 of 50 (block 9) while factoring 114. The two partitions land at 13.7B and 13.9B parameters respectively, against a base MiniMax-H3 transformer of roughly 31B, less than half.

Second, rotated W8A8 quantization. 180 linear layers are quantized to W8A8 INT8 behind a block-diagonal Hadamard rotation, which the project calls convrot.

Third, two-time conditioning. Every token receives both the current noise level t and the step endpoint r, and that is what makes 4-, 6- or 8-step sampling work without classifier-free guidance.

The published repository is at https://github.com/Video-Rebirth/hyperflow-h3-flash and the weights are on Hugging Face under VideoRebirthAI/hyperflow-h3-flash.

9.1GB of weights, but the bill is longer

GGUF quants run from Q3_K_M at 7.2GB up to Q8_0 at 14.9GB, with Q4_K_M at 9.1GB recommended as the default for 24GB GPUs. Three runtimes are supported: ComfyUI, Unsloth Studio and stable-diffusion.cpp, the last of which needs a hyperflow-two-time.patch applied.

The project's own end-to-end measurements are at 1344x768 with 6 steps, covering text encoding, the transformer and both the video and audio VAE decodes. On INT8, an RTX 5090 (32GB) takes 92 seconds for a 5.2 second clip and 551 seconds for a 15 second clip. An RTX 4090 (24GB) takes 130 and 750 seconds. An RTX 3090 (24GB) takes 266 and 1684 seconds. Peak VRAM for the INT8 path is 12.0-12.5 GiB at 5.2 seconds and 21.8-22.4 GiB at 15 seconds. In the same table, a single H200 takes 36 seconds for a 5.2 second clip and 229 seconds for a 15 second one.

Three caveats are worth knowing before you plan around those numbers.

  • 16GB of system RAM is the floor, even though the weights themselves are only 9.1GB. Cards with 16GB of VRAM have not been measured yet.
  • Reference inputs are expensive. A single reference image at a 2048 short edge adds roughly 14,300 tokens, while the clip itself is 37,710 tokens at 5.2 seconds and 109,062 tokens at 15 seconds, and attention cost grows with the square of the token count. With two images, the INT8 transformer takes 2.6-2.9x its text-to-video time; with a mixed set of images, video and audio it takes 5.2-5.8x.
  • The first-run download is about 90GB, or about 68GB with the fp8 text encoder, though the 62GB base transformer itself is never fetched.

NVIDIA wired it into SOL-H3

Video Rebirth describes SOL-H3 as its inference-acceleration partner and says it supports this model from day zero. NVIDIA does ship it: the NVlabs/Sana repository contains a models/minimax_h3/HyperFlow-Flash directory alongside a VALIDATION.md with full measurements.

Those measurements were taken on GB200 using the Sol-H3 runtime rather than the package measured in the table above, so the two sets of numbers are not directly comparable. They were run on 2026-11-05, with the checkpoint pinned to revision 9e9ed14b and byte-identical weight shards recorded in PROVENANCE.json. For text-to-video, a 5 second clip takes 13.0 seconds on one GPU, 3.4 seconds on four and 1.9 seconds on eight. A 15 second clip takes 66.6, 16.1 and 8.5 seconds respectively. Four GPUs producing a 5 second clip in 3.4 seconds is squarely into real-time territory.

What is striking is that VALIDATION.md also lists what is not finished. The GPU numerics gate, the 1/4/8-GPU smoke tests and the re-timing with the released remote code are all marked in progress, and the text-to-video rows report only the sol-engine preset, with no official preset comparison because the earlier official cells used pre-release INT8 kernels and were therefore not reported. The provider itself estimates a 12.7x speedup over the H3 baseline on a single B200, a figure taken from Video Rebirth's own landing page rather than an independent measurement.

The weights carry the license with them

The MiniMax H3 Community License Agreement, dated August 2, 2026, defines "Excluded Territories" as the European Union, the United Kingdom, the Republic of Korea and the United States of America, and the "Applicable Territory" as everywhere else. Video Rebirth's weights are distributed as a Model Derivative of MiniMax-H3 under that same agreement, and the model card states explicitly that the repository is not an official MiniMax product. In practical terms, without authorization from MiniMax, these weights cannot be used in those four regions.

Two further clauses tend to get overlooked: commercial products and services generating more than 20 million US dollars in yearly revenue need separate prior written authorization, and the works and their outputs may not be used to improve any other AI model. Jurisdiction and governing law sit in Hong Kong.

It is easy to conflate the code with the weights here. The inference code on GitHub is Apache-2.0, with the ComfyUI custom nodes under GPL-3.0 and the stable-diffusion.cpp patch under MIT. Open code does not make the weights free to use.

A side note on where the idea came from

The rotated INT8 route was not invented here. The model card credits WAS/Minimax-h3_Singularity_v2_pruned with pioneering rotated INT8 on MiniMax-H3. The HyperFlow series now has three members: the original HyperFlow, which reduced training cost, HyperFlow Infinity, which extended the length of a single generation, and HyperFlow H3 Flash, which cuts latency. Infinity shares its weights with the original HyperFlow, while the 8-step LoRA for the full-size MiniMax-H3 transformer lives in a separate repository.

So what

The community's ability to compress weights has become close to routine. What is still throttling distribution is a license that draws lines along national borders. A model that can generate 768p video with synchronized stereo audio in real time on a consumer GPU remains, for open source enthusiasts in Europe and the United States, a paper benefit rather than a working one. Do you think this combination of open weights with territorial licensing gets fixed first, or becomes the norm?