Modelpublic

llmsforall/Millie-35B-A3B-7GB

sourceHugging Faceapache-2.0updated 23d agoView on Hugging Face

0likes708downloads

Model Card

Millie 35B-A3B 7GB

Millie is a 35B-parameter mixture-of-experts coding and agentic model (3B active per token, 262K context, image input) compressed to run on ordinary hardware. It is derived from Agents-A1, built on the Qwen3.5-35B-A3B architecture; expert weights are stored at ~1.2 bits per weight. A larger 11 GB variant is also available.

Files

File	Size	Contents
Millie-35B-A3B-7GB.gguf	6.3 GB	language model
Millie-35B-A3B-mmproj.gguf	0.6 GB	vision tower (image input)

Running it

The GGUF files require the llmsforall llama.cpp fork, which carries the kernels for their weight format (Metal, Vulkan, CPU); upstream llama.cpp cannot load them:

shell

llama-server -m Millie-35B-A3B-7GB.gguf --mmproj Millie-35B-A3B-mmproj.gguf

License

Apache 2.0 — see LICENSE and NOTICE.