Hugging Face's logo

dboris
/
gemma-4-31b-abliterated-mlx-4bit

Text Generation
MLX
Safetensors
English
gemma4
gemma
abliterated
uncensored
apple-silicon
vision-language-model
4bit
quantized
conversational
Eval Results (legacy)
4-bit precision
Model card Files
xet
 Community

WARNING: This model has degeneration issues

This model is under active development. The current weights cause text degeneration (repetition loops) after ~200-300 tokens. Do not use in production.

A fixed version with gentler abliteration parameters is being developed.

Downloads last month
3,365
Safetensors
Model size
5B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for dboris/gemma-4-31b-abliterated-mlx-4bit

Evaluation results