Model reference · open weights

FastMetal-QAD

Available as managed deployment Video FastVideo Text→video 1 variants 0 dl/mo

FastMetal-QAD is an open-weight video model from FastVideo. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

MakerFastVideo
TypeVideo models
TaskText→video
Runs withfastvideo
Based onFastVideo/FastWan2.1-T2V-14B-Diffusers
Released2026-08-10
Popularity0 downloads / month
LicenceOpen weights

About

What FastMetal-QAD is

3-step text-to-video, INT8 pre-quantized for Apple Silicon.

FastMetal is a family of DMD2-distilled Wan video models with quantization-aware-trained INT8 DiTs. We ship the DiT already quantized, so there is no startup quantization — download, load, generate.

What's inside

This repo is fully self-contained for generation:

PathContents
mlx_dit.safetensors / mlx_dit.jsonINT8 (affine, group-64) DiT — student checkpoint
ema/EMA-smoothed variant of the same DiT
text_encoder/, vae/, tokenizer/, scheduler/everything needed to run standalone (fp16 UMT5 text encoder)

Quickstart

Requires macOS with Apple silicon (MPS) and Python 3.11+:

pip install torch transformers mlx safetensors av imageio imageio-ffmpeg
git clone https://github.com/FastVideo/FastVideo.git
cd FastVideo

# student checkpoint
python examples/inference/basic/mlx_wan_prompt_to_video.py \
  --model-root ./FastMetal-14B-QAD \
  --mlx-checkpoint ./FastMetal-14B-QAD \
  --prompt "a cinematic slow pan over a mountain river at golden hour"

# EMA-smoothed variant
python examples/inference/basic/mlx_wan_prompt_to_video.py \
  --model-root ./FastMetal-14B-QAD \
  --mlx-checkpoint ./FastMetal-14B-QAD/ema \
  --prompt "a cinematic slow pan over a mountain river at golden hour"

Model details

Base modelFastWan 2.1 T2V 14B
DistillationDMD2, 3 denoising steps
Quantizationaffine INT8, group size 64, QAT-trained
Resolution448×832 (480p), 77 frames
Flow shift8.0
DiT weights~15 GB (INT8)

Training

DMD2 distillation of the FastWan 2.1 T2V 14B teacher onto an INT8 student on NVIDIA GB200 clusters, with quantization-aware training (affine INT8, group 64) so the deployed model matches the training objective. Training corpus: FastVideo/Wan-Syn_77x448x832_600k.

FastMetal family

ModelTier
FastMetal-1.3B-QADEntry — 16 GB+ class Macs
FastMetal-5B-QADMid — 720p
FastMetal-14B-QADQuality — 24 GB+/ Ideally 36 Macs

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How video models work

Prompt / imagestart pointTemporal diffusionframes over timeVideoMP4 clipA video model generates a sequence of coherent frames from your prompt or a starting image.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys fastmetal-qad for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (fastmetal-qad 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":"fastmetal-qad","prompt":"a drone shot over a forest"}'

Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms