Maestro v1.6.0 Adds MiniMax H3 Full Model Support and Local Video/Audio Generation
cocktailpeanut · x · 2026-08-08
Maestro releases v1.6.0, bringing major updates for MiniMax H3 models.
- Omni Multimodal Generation: Supports generating new video and synchronized audio from ordered image, video, and sound references. References can be reordered and labeled.
- Models & VRAM: Offers 20B Pruned and 33B Full models. Introduces Match Output mode for consumer GPUs and optimizes memory usage.
- Quantization & Turbo LoRA: Adds multiple text encoder quantization options (NVFP4-AWQ, GGUF, etc.) and supports H3 Turbo LoRA.
- Workflow: Omni generation is capped at 14.4 seconds. The First & Last workflow now supports longer videos by continuing from the preceding final frame.
Related event: Jeff Dean Backs AI Startup Sophont as Second Investor(2 posts)→
More from Infra
- Self-Improving Agents Optimize Inference Stack, Achieving 18% Speedup on B200s — yisongyue · 2026-08-08
- KerasHub Natively Integrates vLLM for Significant Inference Performance Gains — fchollet · 2026-08-08
- What is the Theoretically Optimal Quantization Bit-Width for LLMs? — takuonline · 2026-08-08
- llama.cpp PR Boosts Intel Battlemage Decode Speed by up to 169% at 118K Context — BTA_Labs · 2026-08-08
- Agriculture Bot Powered by XTR-0 Brain: Edge Computing Meets Robotics — mjdramstead · 2026-08-08
- SK Hynix Approves $38B Investment to Expand South Korean Chip Plants — pstAsiatech · 2026-08-08