Downloads · 30 days
31
2% of all-time downloads
Gemma-4-26B-A4B-Heretic-MLX-7bit
TheCluster/Gemma-4-26B-A4B-Heretic-MLX-7bit
Gemma-4-26B-A4B-Heretic-MLX-7bit is a image-text-to-text model from TheCluster. 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 mlx. The card lists the license as apache-2.0.
<div align="center" <img src=https://ai.google.dev/gemma/images/gemma4banner.png </div
All-time downloads
1.5K
Public
Parameters
25.8B
24.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors24.3 GB · 100%
Parameter types
How the weights are stored.
U3224.5B · 95%
Try a prompt
Base models
Model card
From the Hugging Face model README
<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
| Metric | This model | Original model (google/gemma-4-26B-A4B-it) |
|---|---|---|
| KL divergence | 0.0499 | 0 (by definition) |
| Refusals | 11/100 | 100/100 |
Abliteration parameters
| Parameter | Value |
|---|---|
| start_layer_index | 10 |
| end_layer_index | 30 |
| preserve_good_behavior_weight | 0.5480 |
| steer_bad_behavior_weight | 0.0009 |
| overcorrect_relative_weight | 0.5868 |
| neighbor_count | 14 |
Source
This model was converted to MLX format from coder3101/gemma-4-26B-A4B-it-heretic using mlx-vlm version 0.4.4.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- gemma4
- License
- apache-2.0
- Languages
- en, zh, ru, es, fr, it
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026