Downloads · 30 days
25
15% of all-time downloads
gemma-4-31B-it-4bit
DreamFoundries/gemma-4-31B-it-4bit
gemma-4-31B-it-4bit is a text generation model from DreamFoundries. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
[](https://mlxhub.app/open-model?repo=DreamFoundries/gemma-4-31B-it-4bit)
All-time downloads
172
Public
Parameters
30.7B
17.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.3 GB · 100%
Parameter types
How the weights are stored.
U3230.7B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-31B-it MLX 4-bit
This repository contains an MLX-LM conversion of google/gemma-4-31B-it.
Conversion Details
- Original model:
google/gemma-4-31B-it - Model family: Gemma4
- Source model type:
gemma4 - Model size: 32,682,372,656 parameters
- Quantization: MLX-LM affine quantization
- Bits: 4-bit
- Group size: 64
- Local MLX folder size at upload time: 16.11 GiB
- Local safetensors weight size at upload time: 16.08 GiB
This Gemma conversion follows the MLX-LM Gemma 4 shared-KV topology and uses non-strict checkpoint loading so extra HF tensors outside that topology are discarded during conversion.
Usage
mlx_lm.generate --model DreamFoundries/gemma-4-31B-it-4bit --prompt "Hello" --max-tokens 64
Benchmarks
No comparative benchmarks have been run yet. The repository does not currently provide quality, speed, memory, or benchmark comparisons against the original weights or other quantizations.
License
This is a converted/quantized derivative of the original model. Please refer to the original model repository for the upstream license and usage terms: https://huggingface.co/google/gemma-4-31B-it
- Task
- Text Generation
- Library
- mlx
- Type
- gemma4
- License
- apache-2.0
- Created
- Jun 28, 2026
- Updated
- Aug 25, 2026