Downloads · 30 days
17
43% of all-time downloads
gemma-4-31B-it-bnb-8bit
lierseleow/gemma-4-31B-it-bnb-8bit
gemma-4-31B-it-bnb-8bit is a machine learning model from lierseleow. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains quantized weights for google/gemma-4-31B-it.
All-time downloads
40
Public
Parameters
31.3B
32.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.7 GB · 100%
Parameter types
How the weights are stored.
I829.8B · 95%
Base models
Model card
From the Hugging Face model README
lierseleow/gemma-4-31B-it-bnb-8bit (Quantized)
This repository contains quantized weights for google/gemma-4-31B-it.
License & Attribution
Built with Google Gemma 4.
This model is a derivative work of Googles's Gemma 4 and is governed by the Apache 2.0 License, the Gemma Terms of Service and the Gemma Prohibited Use Policy.
- Official License: Apache 2.0 License
- Terms of Service: Gemma Terms of Service
- Prohibited Use Policy: Gemma Prohibited Use Policy
By downloading, copying, or using these quantized weights, you agree to compliance with the terms, conditions, and restrictions outlined.
Quantization Details
- Quantization Method: bitsandbytes
- Bits/Precision: 8bit
- Base Model: google/gemma-4-31B-it
Dependencies Details
- transformers version: 5.14.1
- bitsandbytes version: 0.50.0
- Type
- gemma4
- License
- apache-2.0
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026