MiniMax-H3-f32

About

What MiniMax-H3-f32 is

MiniMax-H3-MLX-f32 MLX (Apple Silicon) build of the MiniMax-H3 diffusion transformer. Unquantized, upcast to float32. Powered by MiniMax H3. These files are modified. The transformer weights have been converted to MLX and widened to float32; 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. This build carries no more information than the bf16 one. MiniMax's weights are bfloat16 on disk, so upcasting to float32 is a lossless widening, not extra precision — you are downloading 132.6 GB of data that fits losslessly in 66.3 GB. It is published for float32 fine-tuning and numerics work, where having the base already widened is convenient. If you only want to generate, take bf16 instead. If you want float32 compute from a smaller download, loaddit(dtype=mx.float32) upcasts at load time and gives an identical model. 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:

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

Specifications

What it is

How it works

How video models work

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.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys minimax-h3-f32 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-h3-f32 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":"minimax-h3-f32","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Licence

Commercial licence needed

Sources

Weights & code

Explore

More video models