I have being using using a cached model lmstudio-community/Qwen3-235B-A22B-GGUF:Q8_0 with llama.cpp for a few weeks, and today, although nothing changed on my side, and apparently the model has not been updated either, llama.cpp started downloading it again today instead of using the download cache…

Did something change recently regarding caching / ETags?

John6666 May 17, 2025, 4:53am 2

I wonder why…
It doesn’t seem like there have been any model changes, so maybe there has been a specification change on the Hub side.

Topic		Replies	Views
Downloaded models Beginners	14	1947	September 15, 2024
Loading a retrained model locally Beginners	2	2373	February 5, 2024
Permission to use Llama 13b didnt update since nov 2024 Beginners	1	20	January 28, 2025
Download llama for offline computer Models	1	1128	September 13, 2023
Why the model loading of llama2 is so slow? 🤗Transformers	6	9412	April 24, 2024