Video models, accelerated and customized for your production.

Post-training, inference optimization, and deployment for the commercial video formats people actually make.

Pending

Coming soon. Join the waitlist for updates and customization for your needs.

What We Do

We take open video models from weight to production

01

Accelerate

Post TrainingModel Adaptation

Reduce latency and serving costs with model-specific optimization tuned to your target hardware and production workload.

02

Customize

Post TrainingModel Adaptation

Adapt open models to your visual language, formats, and workflows while preserving quality and creative control.

03

Deploy

InferenceProduction Systems

Move from weights to a dependable production service with scalable infrastructure, observability, and hands-on support.

Open 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.

MiniMax-H3

Current Work

A technical preview of our ongoing MiniMax H3 optimization work.

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

Pending

Weights / Attention / Linear

Partner

Collaborators

NVIDIA vLLM FastVideo

Working with an open-weight video model?

Talk to us