Downloads · 30 days
529
17% of all-time downloads
Qwen3.8-27B-Heretic-MLX-4bit
TheCluster/Qwen3.8-27B-Heretic-MLX-4bit
Qwen3.8-27B-Heretic-MLX-4bit 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 style="text-align:center; margin-bottom:12pt; font-size:11pt"If you like my work, you can <a href="https://donatr.ee/thecluster/"support me</a<br/</div
All-time downloads
3K
Public
Parameters
27.4B
16.1 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
<div style="text-align:center; margin-bottom:12pt; font-size:11pt">If you like my work, you can <a href="https://donatr.ee/thecluster/">support me</a><br/></div>
Qwen3.8-27B Heretic
Quality: quantized (4-bit, affine, group size: 64)
This is an uncensored version of Qwen/Qwen3.8-27B, made using Heretic v1.4.0.
Update: default reasoning_effort is set to 'low' to avoid overthinking.
Recommended settings
-
Sampling Parameters: The developers suggest using the following sets of sampling parameters:
- Thinking Mode:
temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=0.0,repetition_penalty=1.0 - Instruct (or non-thinking) mode:
temperature=0.7,top_p=0.80,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0
For supported frameworks, you can adjust the
presence_penaltyparameter between 0 and 2 to reduce endless repetition. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance. - Thinking Mode:
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en, zh, ru, es, fr, it
- Created
- Aug 16, 2026
- Updated
- Aug 19, 2026