Skip to content
NewA calmer, faster ZeroHour

Matrix-Game 4.0 renders playable worlds at 480p and 60 FPS

Original title: Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

Hugging Face daily papersby Jihai Zhang, Runjia Qian, Kaiqin Kong ()1 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

An engine plus distilled video renderer reports 112 ms latency on one RTX 5090, with code and weights released.

Matrix-Game 4.0 separates game execution from visual generation. A lightweight engine holds world state and rules, a multimodal coding agent turns player ideas into code and captions, and an autoregressive video renderer turns low-poly proxies into detailed visuals. The renderer is distilled to generate four-frame chunks in one or two denoising steps. Authors report 480p, 60 FPS gameplay on one NVIDIA RTX 5090 and release code, weights, and low-poly assets.

Unconfirmed: Frame rates, latency, and memory figures are author-reported measurements.

Key facts
  • Key-press-to-display latency is reported at 112 ms.
  • Single-step generation reaches 83 FPS with 18.2 GiB peak GPU memory.
  • Fixed prompts reach 67 FPS on an RTX 5080 and 58 FPS on an RTX 5070 Ti.
  • Demonstrations include customizable shooter and driving games.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We outline a roadmap for the next generation of Matrix-Game that separates game execution from visual generation through an executable game harness, and introduce Matrix-Game 4. 0 as the first system built on this design.

Hugging Face daily papers

By Jihai Zhang, Runjia Qian, Kaiqin Kong · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.