vladimirrott /
mojo-dllm
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
Updated 19 min ago
Maintain this repo? Add this badge to your README.
Why now
+231 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It needs a machine that runs Mojo, and an NVIDIA GPU is optional. You point it at a quantized GGUF file of LLaDA-8B or Dream-7B, and it generates text from the command line.
Summary written by AI from the repository’s description and README.
vladimirrott / mojo-dllm
View on GitHub(opens in new tab)