Model reference · open weights
MiniMax-H3 is an open-weight video model from Abiray, 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 (Abiray/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. 📌 Note: Pruned Versions for Consumer GPUs If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the MiniMax-H3-Pruned-GGUF repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. Available Pruned Quants: 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. FL2VA Models: MiniMax-H3-FL2VA-Q3KM.gguf (15.6 GB) MiniMax-H3-FL2VA-Q3KS.gguf (15.6 GB) MiniMax-H3-FL2VA-Q40.gguf (18.6 GB) MiniMax-H3-FL2VA-Q4KM.gguf (19.9 GB) MiniMax-H3-FL2VA-Q4KS.gguf (19.9 GB) MiniMax-H3-FL2VA-Q50.gguf (22.8 GB) MiniMax-H3-FL2VA-Q5KM.gguf (23.9 GB) MiniMax-H3-FL2VA-Q5KS.gguf (23.9 GB) MiniMax-H3-FL2VA-Q6K.gguf (28.2 GB) MiniMax-H3-FL2VA-Q80.gguf (36 GB) Ref2VA Models: MiniMax-H3-Ref2VA-Q3KM.gguf (15.6 GB) MiniMax-H3-Ref2VA-Q3KS.gguf (15.6 GB) MiniMax-H3-Ref2VA-Q40.gguf (18.6 GB) MiniMax-H3-Ref2VA-Q4KM.gguf (19.9 GB) MiniMax-H3-Ref2VA-Q4KS.gguf (19.9 GB) MiniMax-H3-Ref2VA-Q50.gguf (22.8 GB) MiniMax-H3-Ref2VA-Q5KM.gguf (23.9 GB) MiniMax-H3-Ref2VA-Q5KS.gguf (23.9 GB) MiniMax-H3-Ref2VA-Q6K.gguf (28.2 GB) MiniMax-H3-Ref2VA-Q80.gguf (36 GB) Text Encoders qwen3vl32bminimaxh3int4convrot.safetensors (15 GB) qwen3vl32bminimaxh3nvfp4awq.safetensors (27.1 GB) qwen3vl32bminimaxh3-Q4KM.gguf (14.6 GB) VAE Models minimaxh3audiovaefp32.safetensors (605 MB) minimaxh3videovaefp16.safetensors (5.21 GB) 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-vid
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Abiray |
|---|---|
| Type | Video models |
| Variants | 1 |
| Based on | MiniMaxAI/MiniMax-H3 |
| Released | 2026-08-03 |
| Popularity | 1M downloads / month |
| Likes | 127 |
| 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 abiray-minimax-h3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (abiray-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":"abiray-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