# Tencent open-sources Hy-Nomas, a steerable video world model that runs on a single RTX 4090

The Apache 2.0 model generates 720×1280 video at 24 frames per second one segment at a time and accepts new text or camera instructions mid-generation, using a persistent memory cache (a KV cache) that keeps the generated world consistent.

- Published: 2026-10-25T06:22:55.342Z
- Canonical: https://polylog.news/ai/2026-10-25/tencent-open-sources-hy-nomas-a-steerable-video-world-model
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

Tencent Hunyuan released Hy-Nomas on October 23 under the Apache 2.0 license. The release includes weights, code and a 280-case benchmark suite, Hy-Nomas-Bench (explainx). As AI ML Big Data described it, the model builds a world segment by…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-25/tencent-open-sources-hy-nomas-a-steerable-video-world-model (subscription information: https://polylog.news/pricing).