Metraipolis › archive › dc_d9828eb8aa5d

Running a 20B Video Diffusion Transformer on Consumer Hardware: A Deployment and Measurement Report for MiniMax H3 on Apple Silicon — arXiv:2611.00843

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00843
License (as archived)
CC0-1.0
Archived
2026-11-03T18:26:46.975Z
SHA-256 of the archived text
03102d81de2917d0dcc6d066524c0e0e8a63a8bead046b3686006417c2d8e58a
Stable URL of this page
https://metraipolis.com/documento/dc_d9828eb8aa5d

How to cite

Running a 20B Video Diffusion Transformer on Consumer Hardware: A Deployment and Measurement Report for MiniMax H3 on Apple Silicon — arXiv:2611.00843 — arXiv (en), https://arxiv.org/abs/2611.00843 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9828eb8aa5d (Metraipolis archive dc_d9828eb8aa5d, sha256 03102d81de2917d0dcc6d066524c0e0e8a63a8bead046b3686006417c2d8e58a)
BibTeX
@misc{dcd9828eb8aa5d,
  title = {Running a 20B Video Diffusion Transformer on Consumer Hardware: A Deployment and Measurement Report for MiniMax H3 on Apple Silicon — arXiv:2611.00843},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00843},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9828eb8aa5d; sha256 03102d81de2917d0dcc6d066524c0e0e8a63a8bead046b3686006417c2d8e58a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00843. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We report the end-to-end deployment and measurement of MiniMax H3, a 20.38-billion-parameter video diffusion transformer (DiT) - the count measured from the safetensors headers of the Q8 checkpoint as deployed locally (Section 3.2) - running entirely on consumer Apple Silicon hardware: an Apple Mac mini with M5 Pro chip and 64 GiB of unified memory. Using the official bf16-to-Q8 (8-bit, group size 64) quantization path executed locally on the machine, we produced a working text-to-video pipeline with no cloud dependency. We document the full deployment procedure, including two non-trivial blockers and their fixes, and report measured figures for build time, peak memory, and per-clip render latency across four resolution tiers (Draft 384x640 through Native 768x1344). A 15.08-second 576x1024 clip rendered in 4838.49 seconds with a measured MLX peak of 27.467 GiB. We further operated the system as an unattended production pipeline, completing 17 clips in 26.49 hours with zero render failures. A blind human review of the 17 production clips (generation prompts withheld) averaged 3.12, 3.18, and 2.94 out of 5 for structural integrity, temporal consistency, and visible artifacts. All figures in this report are our own measurements except where explicitly labeled as third-party data. This is a systems/empirical report; we make no claim of model innovation.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2611.00843 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:10:22.846Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).