Changes / Feeds / lmstudio-community/Qwen3.8-27B-MLX-6bit
lmstudio-community/Qwen3.8-27B-MLX-6bit
No tracked key changed across the 1 recorded revision since 2026-08-14. Head as last read: 05f38c1f39e2f39619653616fe8e96a5d676358e.
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: 05f38c1f39e2 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-6bit", revision="05f38c1f39e2f39619653616fe8e96a5d676358e")
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-6bit.html)