Model reference · open weights

MiniMax-H3

MiniMax-H3 is an open-weight video model from pipenetwork, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Licence fee required Video pipenetwork 4 variants 3k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What MiniMax-H3 is

MiniMax-H3-MLX-8bit MLX (Apple Silicon) build of the MiniMax-H3 diffusion transformer. Quantized to 8-bit (group size 64). Powered by MiniMax H3. These files are modified. The transformer weights have been converted to MLX and quantized; they are not MiniMax's originals. Everything else about the model is unchanged. What this is MiniMax-H3 generates synchronized video and audio together. It is not a language model: a 33B diffusion transformer denoises video and audio latents jointly over one packed sequence, conditioned by a frozen Qwen3-VL-32B encoder, with separate video and audio VAEs. Running it needs the pipeline code, not just these weights: This repository holds the transformer only. The VAEs and the text encoder come from the upstream release; the pipeline loads them directly. Size The gap is deliberate. ~13B of H3's 33B parameters are the per-block AdaLN projections, whose only input is the timestep embedding. For a fixed sampler schedule every modulation tensor a run needs is precomputed once into a small table, and the projections are then dropped — so they are on disk but never resident. The table scales with step count, not model size: measured at 145 MB for a 9-step schedule and 745 MB for 40 steps, against the 26 GB it replaces. Those projections are quantized to 8-bit here. That was measured, not assumed: quantizing them shifts the modulation table by 0.25%, an order of magnitude less than the 8-bit core's own velocity error, and takes 12.2 GB off this download. (4-bit AdaLN is measurably worse — 0.77% on the table, 2.8% on its worst tensor — and is not used at any core width.) How the widths compare Measured with teacher forcing — one bfloat16 trajectory recorded, each variant re-predicting the velocity at those same latents, so the difference is quantization error alone rather than trajectory divergence. 20 paired observations per variant, aggregated with a paired bootstrap. Every interval is disjoint from its neighbours, so the ranking is solid. Two things worth noting: the steepest step is 6 to 4 bits (2.7x), not at the low end; and audio degrades faster in relative terms than video (its share of the error climbs from 0.40x at 8-bit to 0.82x

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerpipenetwork
TypeVideo models
Parameters (lead)9.4B
Variants4
Runs withmlx
Based onMiniMaxAI/MiniMax-H3
Released2026-08-03
Popularity3k downloads / month
Likes6
LicenceCommercial licence needed

How it works

How video models work

Prompt / imagestart pointTemporal diffusionframes over timeVideoMP4 clipA video model generates a sequence of coherent frames from your prompt or a starting image.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
MiniMax-H3-MLX-8bit9.4BMLXWeights ↗
MiniMax-H3-MLX-4bit6.9BMLXWeights ↗
MiniMax-H3-MLX-bf1633.1BMLXWeights ↗
MiniMax-H3-MLX-6bit8.1BMLXWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys pipenetwork-minimax-h3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (pipenetwork-minimax-h3 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"pipenetwork-minimax-h3","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Tags

mlx safetensors apple-silicon text-to-video image-to-video audio-video-generation diffusion image-text-to-video

Licence

Commercial licence needed

The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗

Sources

Weights & code

Want MiniMax-H3 on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More video models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms