Downloads · 30 days
48
4% of all-time downloads
gemma-4-31B-it-int4-foem
Xingyu-Zheng/gemma-4-31B-it-int4-foem
gemma-4-31B-it-int4-foem is a image-text-to-text model from Xingyu-Zheng. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
The 31B version may encounter an error at languagemodel.model.layers.5.selfattn.qkvproj when deployed with vLLM.
All-time downloads
1.3K
Public
Parameters
31.3B
19.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors19.2 GB · 100%
Parameter types
How the weights are stored.
I3229.3B · 94%
Try a prompt
Base models
Model card
From the Hugging Face model README
⚠️ Warning
The 31B version may encounter an error at language_model.model.layers.5.self_attn.qkv_proj when deployed with vLLM.
This issue appears to originate from GPTQModel, as it does not occur in the E2B version. We are currently investigating and working on a fix.
<div align="center"> <img src=https://ai.google.dev/gemma/images/gemma4_banner.png> </div> This is an unofficial quantized version of google/gemma-4-31B-it.🧠 Quantization Framework
🗺️ Quantization Method
FOEM is an improved quantization method over GPTQ. The resulting model preserves the same inference structure as GPTQ, ensuring compatibility with existing deployment pipelines while achieving better accuracy.
📚 Calibration Dataset
We randomly sampled 512 examples from nohurry/Opus-4.6-Reasoning-3000x-filtered.
📋 Usage Example
This model can be deployed using standard frameworks such as vLLM, just like other GPTQModel-quantized models.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- License
- apache-2.0
- Created
- Apr 3, 2026
- Updated
- Apr 4, 2026