WeeLLM
WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It
- flux
- low-vram
- stable-diffusion
- z-image
- hidream
- krea2
- qwen-image
- qwen-image-edit
- sdxl
- diffusion
- ernie-image
- flux2
- flux2-klein
- hidream-o1
- ideogram-4
- Stars
- 86
- Forks
- 10
- + today
- +1
- Created
- 2mo
Ranking data as of October 12, 2026 (UTC).
Star History
Today, hour by hour
Overview
WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It It ranks #1838 on GitTiger, gaining +1 star on October 12, 2026 (UTC).
The project is written in Python and has 10 forks. It was created 2mo ago.
git clone https://github.com/Jit-Roy/WeeLLM.git
cd WeeLLM
# see README for setup