> ## Content Index
> Fetch the complete content index at: https://globalfeed.ai/llms.txt
> Use this file to discover other available public pages before exploring further.

# GLM-5.3-Flash now runs fully local on the Mac
- URL: https://globalfeed.ai/en/glm-5-3-flash-now-runs-fully-local-on-the-mac/
- Published: 2026-09-01T19:36:06.000Z
- Updated: 2026-09-01T19:36:06.000Z
- Description: Rapid-MLX 0.13.3 runs Z.ai's MIT-licensed GLM-5.3-Flash fully local on Apple Silicon; the 4-bit build averages 30 tokens per second on an M3 Ultra.
- Author: GlobalFeed Editor
- Tags: zai, apple silicon, mlx, glm-5.3-flash, x-rapidmlx, x-Zai_org, dil-en, elle, video, x-gitti

GLM-5.3-Flash, the model Z.ai published as open weights under an MIT license on August 26, now runs on a Mac without touching the cloud. Rapid-MLX, an inference engine built for Apple Silicon, shipped production-ready support for it in version [0.13.3](https://pypi.org/project/rapid-mlx/0.13.3/?ref=globalfeed.ai).

## 30 tokens per second on an M3 Ultra

The engine, which Raullen Chai built on top of Apple's MLX framework, averages 30 tokens per second with the 4-bit checkpoint across a 512-token generation on an M3 Ultra. On a 192 GB unified-memory machine the model holds 165 GB of active memory, which fits the 320B-total, 18B-active MoE architecture onto a single desktop.

Installation is a single "pip install -U rapid-mlx"; a desktop app is available at [rapidmlx.com](https://rapidmlx.com/download?ref=globalfeed.ai). Because the engine exposes an OpenAI-compatible API, tools like Claude Code and Cursor can point at the local model directly.

A chart shared with the announcement places GLM-5.3-Flash at 57 on the Intelligence Index, just below the Claude Opus family and above most large models. Z.ai covered the 1M-token context window and the MIT license in its [launch post](https://x.com/Zai%5Forg/status/2092616204787626030?ref=globalfeed.ai).