Downloads · 30 days
1.5K
21% of all-time downloads
gemma-4-31B-it-INT8
lokeshe09/gemma-4-31B-it-INT8
gemma-4-31B-it-INT8 is a image-text-to-text model from lokeshe09. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
INT8 quantization of google/gemma-4-31B-it, produced with llm-compressor.
All-time downloads
6.8K
Public
Parameters
31.3B
33.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors33.3 GB · 100%
Parameter types
How the weights are stored.
I829.3B · 94%
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-31B-it-INT8
INT8 quantization of google/gemma-4-31B-it, produced with llm-compressor.
Vision encoder, lm_head, embeddings, and norm layers are kept in original precision.
- Task
- Image-Text-to-Text
- Type
- gemma4
- License
- gemma
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026