realrebelai/FastH3-V2_GGUFs
text-to-video model by realrebelai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
GGUF quantizations of FastVideo FastH3 8-Step V2 for use with ComfyUI / ComfyUI-GGUF. These GGUFs were converted from the full official BF16 FastH3 V2 transformer weights released by FastVideo. Original model: https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2 FastH3 8-Step V2 is a distilled MiniMax-H3 checkpoint from FastVideo designed to generate synchronized video and audio using only 8 transformer forwards. The official V2 release uses: Additional quantizations may be added later. The official FastH3 V2 transformer is distributed as a large sharded BF16 checkpoint. For these releases, the complete transformer was reconstructed and converted to the tensor layout expected by ComfyUI before GGUF quantization. The conversion preserves the FastH3 architecture, including: High-precision projection/conditioning tensors are preserved as F16/F32 where appropriate rather than indiscriminately quantizing every tensor. ComfyUI-GGUF is required. Place the downloaded GGUF in: Restart ComfyUI or refresh your model list after installing the model. Load the model using your GGUF unet loader. FastH3 V2 is…
Read the full model card ↗ · Preview checked 2026-09-21T06:52:39.921Z
Inside the original model card — Document outline
- FastH3 V2 GGUFs
- Model
- Available GGUFs
- Full-Weight Conversion
- ComfyUI Installation
- Recommended Generation Settings
- Required Supporting Models
- ⚠️ GGUF Text Encoder / WAN Architecture Users
- VAE Files
- Q4KM
- Important: VSA / Attention
- Scope
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
realrebelai/FastH3-V2_GGUFs is a text-to-video model repository published by realrebelai on Hugging Face. The source reports the comfyui library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- comfyui
- Recent downloads (30 days)
- 4,019
- Cumulative likes
- 16
- Hugging Face trending score
- 16
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-09-16T03:27:17.000Z
- Last modified
- 2026-09-17T04:39:09.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: FastVideo/FastVideo-FastH3-8-Step-V2
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-21T06:36:50.330Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-T2V-A14B-GGUF
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree
Wan-AI/Wan2.1-T2V-1.3B-Diffusers
larryvrh/MiniMax-H3-Turbo-Lora