Bonus: Top up now and we'll double your first deposit — get x2 credits instantly.

Minimax-h3-Turbo: Self-Hosting & Deployment Guide

Minimax-h3-Turbo is an open-weight image-to-video generation model.

What is Minimax-h3-Turbo?

Minimax-h3-Turbo is an open-weight image-to-video generation model, published by lightx2v with open weights at lightx2v/Minimax-h3-Turbo. LLM API does not route this model today, so there is no endpoint or code sample for it here. What this page does give you is the self-hosting picture: published weight sizes, the VRAM each quantisation needs and the commands to serve it yourself. Every figure is read from the public repository and refreshed weekly. At import it had 1,561,416 downloads on Hugging Face in the previous 30 days, under the apache-2.0 licence.

How to run Minimax-h3-Turbo yourself

Open weights (apache-2.0). Below: how much memory the weights need at each quantization, which hardware fits them, and the commands to serve it.

Minimax-h3-Turbo VRAM requirements

Precision / quantizationWeightsFigureSource
Full precision weights58.8 GBFile sizelightx2v/Minimax-h3-Turbo

File size = actual download size on Hugging Face. Estimate = parameter count × bytes per weight. Weights only — the KV cache for long contexts needs extra memory; the fit tables below add 15% headroom as a rule of thumb.

GPU requirements: deploy Minimax-h3-Turbo on your hardware

HardwareFull precision weights
NVIDIA H200141 GB1×
NVIDIA H10080 GB1×
NVIDIA A100 80GB80 GB1×
NVIDIA L40S48 GB2×

GPUs needed per variant.

HardwareFull precision weights
AWS p5.48xlarge8× H100 · 640 GBFits
AWS p4de.24xlarge8× A100 80GB · 640 GBFits
AWS g6e.12xlarge4× L40S · 192 GBFits
Google Cloud a3-highgpu-8g8× H100 · 640 GBFits
Azure ND H100 v58× H100 · 640 GBFits

Whole-instance GPU memory; public instance specs.

Not on LLM.API yet

We do not route this model through our API at the moment. Browse the models you can call today — most workloads have a close match already live.

Not available on LLM API yet

We do not route this model through our API at the moment, so there is no endpoint or code snippet for it yet. Browse the models you can call today — most workloads have a close match already live.

Browse available models

When to Use — When NOT to Use

Use it if...

  • You need images generated from a text prompt, or edited from a reference image (Minimax-h3-Turbo)
  • You want image generation on the same LLM API key as your text models, with no extra vendor SDK
  • Your pipeline can take the result as a URL or base64 payload rather than a streamed response
  • You want per-image pricing you can read off the catalogue before you commit

Avoid if...

  • You need a chat, coding or reasoning model — this model returns images, not text
  • You need token-by-token streaming: image calls return once the picture is finished
  • You need video, speech or embeddings; those are separate models in the catalogue
  • Your licensing review has not cleared generated imagery for commercial use

Get one key to every model

Swap your API key. Keep your code.