Model reference · open weights
MiniMax-H3 is an open-weight video model from molbal, 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.
About
MiniMax H3 (GGUF Quantizations) This repository (molbal/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. Repository Contents UNet Models (GGUF) This repository includes quantized versions of both the FL2VA (First-and-last-frame mode) and Ref2VA (Omni-reference mode) base models. The FL2VA builds are pruned to FP8 first and then quantized to GGUF. FL2VA Models (pruned to FP8): minimaxh3fl2vaprunedfp8Q40.gguf (11.4 GB) minimaxh3fl2vaprunedfp8Q80.gguf (20.2 GB) minimaxh3fl2vaprunedfp8Q8CR.gguf (20.2 GB) minimaxh3fl2vaprunedfp8U16G.gguf (15.0 GB) Ref2VA Models: minimax-h3-ref2va-Q40.gguf (11.4 GB) minimax-h3-ref2va-Q80.gguf (21.4 GB) minimax-h3-ref2va-Q8CR.gguf (20.2 GB) minimax-h3-ref2va-U16G.gguf (15.0 GB) Quantization formats Note: Q8CR and U16G are specifically created to work with the molbal/CofmyUI-GGUF ComfyUI custom nodes and will probably not work elsewhere. Model Variants and Input Specifications H3-Base-FL2VA: First-and-last-frame mode. Supports zero, one, or two input images. No image input: Text-to-video mode. One image input: First-frame-to-video or last-frame-to-video generation. Two image inputs: First-and-last-frame-to-video generation. H3-Base-Ref2VA: Omni-reference mode. Supports multi-modal reference inputs: Images: ≤ 9 images. Videos: ≤ 3 clips; each clip must be 2–15 seconds long; total duration ≤ 15 seconds. Audio: ≤ 3 clips; audio must be accompanied by image or video input and cannot be used as the sole input; each clip must be 2–15 seconds long; total duration ≤ 15 seconds. Mixed inputs: Maximum number of files across all input types is 12. Output Specifications Output duration: 4–15 seconds. Output aspect ratio: Supports a wide range of aspect ratios, including but not limited to 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16. Output resolution: Supports various resolution dimensions. The shorter side is set to 768 pixels by def
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | molbal |
|---|---|
| Type | Video models |
| Variants | 1 |
| Based on | MiniMaxAI/MiniMax-H3 |
| Released | 2026-08-03 |
| Popularity | 222k downloads / month |
| Likes | 53 |
| Licence | Commercial licence needed |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MiniMax-H3-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys molbal-minimax-h3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (molbal-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":"molbal-minimax-h3","prompt":"a drone shot over a forest"}'
Details
Tags
Licence
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 ↗
Explore