mod
Gemma-3-27B-IT-QAT-GGUF (Q4_0)
by Oleg Skutte
The 27B instruction-tuned version of the Gemma 3 model in GGUF format using Quantization Aware Training (QAT). The GGUF corresponds to Q4_0 quantization. Thanks to QAT, the model is able to preserve similar quality as bfloat16 while significantly reducing the memory requirements to load the model...
- Latest version
- no release indexed
- Downloads
- 137
- Rating
- 1
- Filed under
- Local Models
- Updated
- 9 mo ago
- Available on
- Steam Workshop
Download
Delivered through the Steam client, not a file this page can link to.
Frequently asked
How do I install Gemma-3-27B-IT-QAT-GGUF (Q4_0)?
Install the matching loader first, then put the downloaded file in your mods folder and start the game. The loader, the mod and DREAMIO: AI-Powered Adventures all have to be on the same version, which is the usual reason a mod does not appear in game.
Where do I download Gemma-3-27B-IT-QAT-GGUF (Q4_0) safely?
From the author's own page on Steam Workshop, which is where the data here is synced from. IndexGG never mirrors, re-hosts or repackages a file: every download button points at the original source, so you get exactly what the author published.
Which DREAMIO: AI-Powered Adventures versions does Gemma-3-27B-IT-QAT-GGUF (Q4_0) work on?
The author has not declared a supported version in the metadata we sync, so there is nothing here we can state as fact. Check the project's own page before installing it, and treat an old mod with no declared version as untested on modern DREAMIO: AI-Powered Adventures.