Downloads · 30 days
102
9% of all-time downloads
Barcenas-Qwen3.8-27B-Fable
Danielbrdz/Barcenas-Qwen3.8-27B-Fable
Barcenas-Qwen3.8-27B-Fable is a image-text-to-text model from Danielbrdz. 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 transformers. The card lists the license as apache-2.0.
All-time downloads
1.1K
Public
Parameters
26.9B
53.8 GB on disk
Likes
5
Public
Repo makeup
Click a slice to open those files.
.safetensors53.8 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026
- SHA
- ca001d49
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Barcenas Qwen 3.8 27b Fable
Based on Qwen 3.8 27B and trained using the saidutta69/fable-5-premium dataset.
It is the most powerful LLM I have trained, with performance comparable to GPT 5.6 Luna and larger models.
It utilizes a dataset focused on high-quality chat data distilled from Claude Fable 5 to enhance the conversational capabilities—an area where Qwen typically leaves room for improvement.
This combination results in an LLM that can run on a single GPU, delivering conversations that rival those of proprietary models.
Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5_text
- License
- apache-2.0
- Languages
- en
- Created
- Aug 18, 2026
- Updated
- Aug 18, 2026