01
Accelerate
Reduce latency and serving costs with model-specific optimization tuned to your target hardware and production workload.
FastH3 technical pathVideo models, accelerated and customized for your production.
Production grounding and evaluation for FastH3: MiniMax H3, post-trained and optimized by FastVideo.
What We Do
We take open video models from weight to production
02
Customize
Adapt open models to your visual language, formats, and workflows while preserving quality and creative control.
FastH3 post-training03
Deploy
Move from weights to a dependable production service with scalable infrastructure, observability, and hands-on support.
FastH3 resultsOpen Weights
We believe open video models will remain a critical part of the production stack. The Nuva Lab team has contributed to open-source AI for years. We optimize open-weight models for production today and will continue supporting and contributing to the models that come next.
FastH3
Current Work
MiniMax H3, post-trained and optimized by FastVideo.
Sparsity Kernel
T2V Validated
Omni Ref Pending
90% Sparse≈10× fewer target-video QK/PV block pairs
Quantization-Aware Distillation (QAD)
T2V Validated
Omni Ref Pending
12.5× Speedup50 → 4 denoising steps
NVFP4 Native
PendingWeights / Attention / Linear
Releases & News
Open model work, production integrations, and ecosystem releases from Nuva Lab and our collaborators.
FastH3 Goes Local
LatestThe FastVideo ecosystem brings FastH3 to NVIDIA DGX Spark and Apple Silicon for local video generation.
MiniMax H3 on vLLM-Omni
vLLM-Omni details the complete MiniMax H3 serving stack and its integration with FastVideo's four-step FastH3.
FastH3 Preview v1
Open-weight, four-step sparse-distilled MiniMax H3, developed with FastVideo and NVIDIA collaborators and grounded in production workloads with Nuva Lab.
Partner
Collaborators
