Changes / Feeds / lmstudio-community/Qwen3.8-27B-MLX-4bit
lmstudio-community/Qwen3.8-27B-MLX-4bit
No tracked key changed across the 1 recorded revision since 2026-08-14. Head as last read: 6067b15cf581666a4aecf6af3afaba4bb5efc20c.
Declares Qwen/Qwen3.8-27B as its base but has a different set of tensors: 851 align (659 of them changed), 1329 are new and 348 of the base's are gone. Compared tensor by tensor from sha256 fingerprints: 6067b15cf581 against Qwen/Qwen3.8-27B at 1d4bf0f2ff60. A hash is equal or not; it says nothing about what an edit does.
Pin it, and let a bot move the pin
from_pretrained("lmstudio-community/Qwen3.8-27B-MLX-4bit", revision="6067b15cf581666a4aecf6af3afaba4bb5efc20c")
With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/lmstudio-community/Qwen3.8-27B-MLX-4bit.html)