Model reference · open weights
MiniMax-H3-Pruned 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 Pruned GGUF This repository (Abiray/MiniMax-H3-Pruned-GGUF) provides pruned and quantized GGUF weights for the MiniMax H3 omni-modal generative model. MiniMax H3 is designed for unified multimodal context processing, capable of generating synchronized high-definition video and 32 kHz stereo audio from text, image, audio, and video inputs. 🌟 Key Highlights VRAM Efficiency: Pruned architecture compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution to consumer-tier GPUs. Synchronized Omni-Modal Output: Simultaneous generation of video (24 FPS) and native stereo audio (32 kHz). Native ComfyUI Support: Directly compatible with standard ComfyUI-GGUF workflows using the native MiniMax backend. Dual Pipeline Variants: Full quant suites for both FL2VA (First/Last Frame) and Ref2VA (Omni-Reference) modes. 📂 Repository Weights & Quantization Breakdown Note: For optimal performance, Q4KM is recommended for 16 GB GPUs, while Q5KM is recommended for GPUs with 24 GB VRAM. FL2VA Models (First-and-Last-Frame Mode) Ref2VA Models (Omni-Reference Mode) ⚙️ Quickstart & ComfyUI Deployment Requirements ComfyUI: Version v0.30.0 or higher is required for native MiniMax-H3 architecture support. Extension: ComfyUI-GGUF custom node package installed. Setup Steps 1. Download your desired .gguf variant from the table above. 2. Place the downloaded .gguf file into the ComfyUI/models/unet/ directory. 3. In your ComfyUI workflow, load the model using the UnetLoaderGGUF node. 📋 Model Variants & Input Specifications H3-Base-FL2VA (First-and-Last-Frame Mode): No image input: Operates as standard Text-to-Video / Text-to-Audio-Video. Single image input: Generates video conditioned on the initial frame or final frame. Dual image input: Interpolates seamlessly between designated first and last reference frames. H3-Base-Ref2VA (Omni-Reference Mode): Images: Up to 9 reference images. Videos: Up to 3 video clips (2–15 seconds per clip; total combined duration $\le$ 15s). Audio: Up to 3 audio clips (must be accompanied by visual input; duration 2–15s). Combined Context: Maximum of 12 multi-modal input assets allowed per prompt. 📊 Output Specifications Duration: 4 – 15 seconds. Aspec
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 | 2026-08-07 |
| Popularity | 234k downloads / month |
| Likes | 56 |
| 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-Pruned-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys minimax-h3-pruned for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-h3-pruned 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-pruned","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