yanun0323 /
Whallm
DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook
Updated 54 min ago
+2 stars gained this week
Stars gained each day, last 30 days
Usual pace · 2 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
Whallm is a Mac app for Apple Silicon that runs large models by keeping common weights in memory and streaming experts from SSD. It includes a chat UI and an OpenAI-compatible local server, and needs macOS 15 or later with a fast SSD.
Summary written by AI from the repository’s description and README.
yanun0323 / Whallm
View on GitHub(opens in new tab)