FastVideo 视频模型 · 模型发布· FastVideo·· 2026-10-17PicksAI score60
FastVideo releases FastH3-QAD-v2 video-audio model
FastVideo/FastH3-QAD-v2
AI briefing
FastVideo releases FastH3-QAD-v2, an 8-step video and audio model trained with NVFP4 weights and quantization-aware distillation (QAD), runnable on a single Blackwell GPU (RTX 5090, RTX PRO 6000) or DGX Spark.
Why it matters
The 8-step video and audio model lands on a single Blackwell GPU with NVFP4 quantized weights, and error data versus the BF16 teacher model is provided.
Open original huggingface.co
Video GenerationDubbing and AudioModel Releases#Model release#Video generation#Voice & audio#Hugging Face