CogVideoX-Fun

3 aliases · CogVideoX-Fun V1.5 5B in q4 / q8 / bf16. Experimental single-worker backend — the smallest RAM footprint of the video lane. Output is video-only.

Experimental single-worker backend. The MVP covers one-second, 672×384 text-to-video. The pinned MLX runtime ships inside rapid-mlx — no source checkout or PYTHONPATH surgery. Weights load lazily on the first job, not at boot.

family

CogVideoX-Fun (Zhipu / VideoX-Fun)

aliases

3

audio

none — video-only

install

pip install 'rapid-mlx[video]'

also needs

ffmpeg · Python 3.11+

OpenAI base URL

http://localhost:8000/v1

Download

Every alias on this page downloads with one command — the pull buttons in the tables below copy it. All 3 aliases on this page are mirrored on the rapid-mlx CDN — our fresh-install test measured CDN pulls at 90 MB/s, with automatic mid-pull fallback to Hugging Face if a mirror file slows down. Weights land in the standard Hugging Face cache, and rapid-mlx serve pulls automatically on first use. Live mirror status →

Usage

rapid-mlx serve cogvideox-fun-5b-q4

curl http://127.0.0.1:8000/v1/videos \
  -F model=cogvideox-fun-5b-q4 \
  -F 'prompt=a fox running through fresh snow, cinematic tracking shot' \
  -F seconds=1 \
  -F size=672x384

Aliases

Frequently asked questions

Does CogVideoX run locally on a Mac?

Yes — CogVideoX-Fun V1.5 5B serves through POST /v1/videos in q4, q8 and bf16, entirely on Apple Silicon. The current scope is one-second 672×384 text-to-video.

How much RAM does CogVideoX-Fun need?

24 GB for q4 (~14.5 GB peak resident) and q8; 32 GB for bf16 — the smallest-RAM entry point to local video generation on rapid-mlx.

Where next