Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text to video

FastVideo-FastH3-8-Step-V2

by Joshua Stone FanzCEO/FastVideo-FastH3-8-Step-V2

FastVideo-FastH3-8-Step-V2 is an open-weight model for text to video from Joshua Stone, released under other. It has 35B parameters. At 16-bit it needs about 84.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.

The FastH3 8-Step V2 checkpoint from FastVideo. It generates synchronized video and audio from text with eight transformer forwards. This step-1300 model was trained with data-free DMD2 and VSA-H3 at 80% sparsity.

Parameters35B
Context—
Weights147.8 GB
Licenseother
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve FastVideo-FastH3-8-Step-V2 (35B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 70.1 GB 84.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x MI325X $2.00 · 1x MI355X $2.59
8-bit 35.0 GB 42.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 17.5 GB 21.0 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.

FastVideo-FastH3-8-Step-V2 on every accelerator the SAVRN Index prices, at every precision

Model Card

The FastH3 8-Step V2 checkpoint from FastVideo. It generates synchronized video and audio from text with eight transformer forwards. This step-1300 model was trained with data-free DMD2 and VSA-H3 at 80% sparsity. Install uv, then use the CUDA 13 / Blackwell path below. It selects FastVideo's published CUDA kernel wheel instead of compiling the kernel locally. See the for other platforms. The tested defaults use four B200 GPUs and the trained eight-forward schedule. On other multi-GPU CUDA systems, follow the installation guide and add --no-replicated-dit --vsa-kernel triton --no-fa4. The GPU count must divide H3's 56 attention heads. This checkpoint supports text-to-audio-video generation.…

Excerpt from the card by Joshua Stone, licensed other.

Identity and Version

Repository
FanzCEO/FastVideo-FastH3-8-Step-V2
Publisher
Joshua Stone
Task
Text to video
Modality
Video
Library
diffusers
Parameters
35B parameters
Languages
few-step
Revision
a68165b7ef6dbe29a6edb0f8854f2d6fae5635c4
First published
2026-09-22
Last updated
2026-09-22

Files and Weights

68 files, 147.9 GB in total. The weights are 32 files totalling 147.8 GB in safetensors.

Weights32 files · 147.8 GB
Configuration19 files · 275.6 KB
Tokenizer12 files · 34.5 MB
Documentation4 files · 33.3 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
audio_vae/diffusion_pytorch_model.safetensorsWeights605.4 MB 52c59e67ba8d
text_encoder/model-00001-of-00014.safetensorsWeights4.9 GB 6b9dfbc930e5
text_encoder/model-00002-of-00014.safetensorsWeights4.9 GB d8bb44b4ff30
text_encoder/model-00003-of-00014.safetensorsWeights4.9 GB 54f22e8b3168
text_encoder/model-00004-of-00014.safetensorsWeights4.9 GB ad09c74d3c13
text_encoder/model-00005-of-00014.safetensorsWeights4.9 GB fc993c8a0e2a
text_encoder/model-00006-of-00014.safetensorsWeights4.9 GB 82f05620d1f7
text_encoder/model-00007-of-00014.safetensorsWeights4.9 GB fb91da8cb01f
text_encoder/model-00008-of-00014.safetensorsWeights4.9 GB 431ca56535c8
text_encoder/model-00009-of-00014.safetensorsWeights4.9 GB 3825e3f4302f
text_encoder/model-00010-of-00014.safetensorsWeights4.9 GB aded5a4d1d5e
text_encoder/model-00011-of-00014.safetensorsWeights4.9 GB 3820ffe8d8d6
text_encoder/model-00012-of-00014.safetensorsWeights4.9 GB 05ad2d08ce71
text_encoder/model-00013-of-00014.safetensorsWeights4.9 GB b64f22898712
text_encoder/model-00014-of-00014.safetensorsWeights3.3 GB e45b6c9998c7
transformer/diffusion_pytorch_model-00001-of-00014.safetensorsWeights5.3 GB b82974a058b5
transformer/diffusion_pytorch_model-00002-of-00014.safetensorsWeights5.3 GB 05568fca94d8
transformer/diffusion_pytorch_model-00003-of-00014.safetensorsWeights5.3 GB ec8885fa237d
transformer/diffusion_pytorch_model-00004-of-00014.safetensorsWeights4.9 GB 70dcbf6d3efb
transformer/diffusion_pytorch_model-00005-of-00014.safetensorsWeights5.3 GB cabab8f1b8d5
transformer/diffusion_pytorch_model-00006-of-00014.safetensorsWeights5.2 GB 9bb11d605a7c
transformer/diffusion_pytorch_model-00007-of-00014.safetensorsWeights5.3 GB bcb3ac184575
transformer/diffusion_pytorch_model-00008-of-00014.safetensorsWeights5.3 GB 845041576ed2
transformer/diffusion_pytorch_model-00009-of-00014.safetensorsWeights4.9 GB ad34ff06d42a
transformer/diffusion_pytorch_model-00010-of-00014.safetensorsWeights5.3 GB 0efb2a0fd04d
transformer/diffusion_pytorch_model-00011-of-00014.safetensorsWeights5.2 GB 32f04fe41845
transformer/diffusion_pytorch_model-00012-of-00014.safetensorsWeights5.3 GB 903eccb1a109
transformer/diffusion_pytorch_model-00013-of-00014.safetensorsWeights5.3 GB 018db4d6d8fe
transformer/diffusion_pytorch_model-00014-of-00014.safetensorsWeights2.1 GB 160b0f5a830b
vae/diffusion_pytorch_model-00001-of-00003.safetensorsWeights5.1 GB 72f4c6be84ac
vae/diffusion_pytorch_model-00002-of-00003.safetensorsWeights5.0 GB 2e05e8bc23fa
vae/diffusion_pytorch_model-00003-of-00003.safetensorsWeights398.5 MB c05d6ac4b1a3
audio_scheduler/scheduler_config.jsonConfiguration97 B —
audio_vae/config.jsonConfiguration2.3 KB —
checkpoint_content.jsonConfiguration3.9 KB —
checkpoint_metadata.jsonConfiguration6.6 KB —
fastvideo_inference.jsonConfiguration977 B —
modular_model_index.jsonConfiguration3.1 KB —
processor/chat_template.jsonConfiguration5.5 KB —
processor/preprocessor_config.jsonConfiguration390 B —
processor/video_preprocessor_config.jsonConfiguration385 B —
scheduler/scheduler_config.jsonConfiguration98 B —
text_encoder/chat_template.jsonConfiguration5.5 KB —
text_encoder/config.jsonConfiguration1.5 KB —
text_encoder/model.safetensors.index.jsonConfiguration97.8 KB —
text_encoder/preprocessor_config.jsonConfiguration390 B —
text_encoder/video_preprocessor_config.jsonConfiguration385 B —
transformer/config.jsonConfiguration546 B —
transformer/diffusion_pytorch_model.safetensors.index.jsonConfiguration70.1 KB —
vae/config.jsonConfiguration2.0 KB —
vae/diffusion_pytorch_model.safetensors.index.jsonConfiguration74.2 KB —
LICENSEDocumentation17.6 KB —
LICENSE-Qwen3-VLDocumentation11.4 KB —
NOTICEDocumentation1.1 KB —
README.mdDocumentation3.3 KB —
.gitattributesRepository1.5 KB —
processor/merges.txtTokenizer1.7 MB —
processor/tokenizer.jsonTokenizer7.0 MB —
processor/tokenizer_config.jsonTokenizer11.0 KB —
processor/vocab.jsonTokenizer2.8 MB —
text_encoder/merges.txtTokenizer1.7 MB —
text_encoder/tokenizer.jsonTokenizer7.0 MB —
text_encoder/tokenizer_config.jsonTokenizer11.0 KB —
text_encoder/vocab.jsonTokenizer2.8 MB —
tokenizer/merges.txtTokenizer1.7 MB —
tokenizer/tokenizer.jsonTokenizer7.0 MB —
tokenizer/tokenizer_config.jsonTokenizer11.0 KB —
tokenizer/vocab.jsonTokenizer2.8 MB —

License and Download

License
other
Access
Open weights, no gate
Download size
147.8 GB
Download from Joshua Stone

Released by Joshua Stone through its official repository on Hugging Face.

Built From

Memory Requirements

PrecisionWeights in memory
As published147.8 GB
16-bit70.1 GB
8-bit35.0 GB
4-bit17.5 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About FastVideo-FastH3-8-Step-V2

How much GPU memory does FastVideo-FastH3-8-Step-V2 need?

About 84.1 GB at 16-bit and 21 GB at 4-bit: the weights (35B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run FastVideo-FastH3-8-Step-V2 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What license is FastVideo-FastH3-8-Step-V2 released under?

other, as its publisher declares it. Read the license text before commercial use.

Similar Models

The recommended FastH3 Preview v1 checkpoint from FastVideo. It generates synchronized video and audio from text with four transformer forwards. This step-1300 model was trained with data-free DMD2 and VSA-H3 at 90% sparsity. Install uv, then use the CUDA 13 / Blackwell path below. It selects FastVideo's published CUDA kernel wheel instead of compiling the kernel locally. See the for other platforms. The tested defaults use four B200 GPUs and the trained four-forward schedule. On other multi-GPU CUDA systems, follow the installation guide and add --no-replicated-dit --vsa-kernel triton --no-fa4. The GPU count must divide H3's 56 attention heads. This preview supports text-to-audio-video…

Open weights other 35B parameters diffusers
View model

Model · Text to video

LTX-2.5-Diffusers

LTX.io

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. Encoding always uses vae/, and LTX2Pipeline decodes with vae/ too. The diffusion decoder is a diffusion model in its…

Access requested at publisher other 19B parameters diffusers
View model

We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository contains our T2V-A14B model, which supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On our new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across most key evaluation dimensions. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2…

Open weights apache-2.0 14.3B parameters diffusers
View model

Model · Text to video

Wan2.2-T2V-A14B-Diffusers

Wan-AI

We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: This repository contains our T2V-A14B model, which supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On our new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across most key evaluation dimensions. Your browser does not support the video tag. If your research or project builds upon Wan2.1 or Wan2.2, we welcome you to share it with us so we can highlight it for the broader community. - Wan2.2…

Open weights apache-2.0 14.3B parameters diffusers
View model

Model · Text to video

Wan2.1-T2V-14B-Diffusers

Wan-AI

In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B…

Open weights apache-2.0 14.3B parameters diffusers
View model

Model · Text to video

Wan2.1-T2V-14B

Wan-AI

In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Your browser does not support the video tag. - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B…

Open weights apache-2.0 14.3B parameters diffusers
View model