MiniMax H3 video generated locally on a 3080 Ti: 12-part series rendered free in 6 hours
cocktailpeanut · x · 2026-09-04
Developer @skyinspired ran MiniMax H3 locally on a laptop 3080 Ti using Pinokio and Maestro, one-shot prompting multi-window video concepts for a planned 12-part custom series. Rendering took 6 hours, entirely free—no paid AI service credits needed. cocktailpeanut shared the demo.
More from Infra
- LLM Token Expenditure Index Falls Below $1, Down Over 50% From Summer Peak — churchkey · 2026-09-04
- Cerebras unveils CS-4 and WSE-3 Turbo, claiming 30x GPU inference speed — airesearch12 · 2026-09-04
- LlamaNet turns idle Macs and GPUs into an OpenAI-compatible community inference network — machaao · 2026-09-04
- Thread coarsening cuts CUDA matmul kernel to 0.41ms on T4, 1.7x speedup with tiling — goyal__pramod · 2026-09-04
- The Next Token Ep.05: Michelle Chen on AI inference at scale, open weights and burning money — ritakozlov · 2026-09-04
- OpenAI's automated jailbreak red-teaming of Astra burned ~200K A100-equivalent GPU-hours — haider1 · 2026-09-04