TheCluster/Gemma-4-26B-A4B-Heretic-MLX-7bit

<div align="center"> <img src=https://ai.google.dev/gemma/images/gemma4_banner.png> </div>

Gemma-4-26B-A4B Heretic

Quality: quantized (*mixed quants per tensor, group size: 32, 7.551 bpw*)

The various layers use 6-, 7-, or 8-bit affine quantization with a group size 32; embeddings are saved in bf16.

This is a abliterated (uncensored) version of google/gemma-4-26B-A4B-it, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method (with row-norm preservation)

Performance

Abliteration parameters

Source

This model was converted to MLX format from `coder3101/gemma-4-26B-A4B-it-heretic` using mlx-vlm version 0.4.4.