Downloads · 30 days
10
11% of all-time downloads
nbeerbower_Gemma4-Gutenberg-31B-LoRA
zeroxjason200/nbeerbower_Gemma4-Gutenberg-31B-LoRA
nbeerbower_Gemma4-Gutenberg-31B-LoRA is a machine learning model from zeroxjason200. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Quick Q80 gguf of this LORA for Gemma4 31B.
All-time downloads
91
Public
Repo size
520 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf520 MB · 100%
At a glance
- Access
- Public
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026
- SHA
- 240d8b0b
Base models
Model card
From the Hugging Face model README
Description
Quick Q8_0 gguf of this LORA for Gemma4 31B.
Load it on top of any Gemma4 31B model by sticking --lora path/to/lora/nbeerbower_Gemma4-Gutenberg-31B-Q8_0.gguf on the end of your llama-server command line.
Tried it with Artemis 31B, changes the text pretty drastically.
You might need to reduce your context a little, I got an OOM when I first ran this without setting a contxt size. It'll probably not perform well with MTP either.
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026