Downloads · 30 days
64
2% of all-time downloads
qwen3-4B-self-thinking_4bit
uberkie/qwen3-4B-self-thinking_4bit
qwen3-4B-self-thinking_4bit is a text generation model from uberkie. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: uberkie - License: apache-2.0 - Finetuned from model : uberkie/qwen3-4B-self-thinking-16bit
All-time downloads
2.7K
Public
Parameters
4.1B
26.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.7 GB · 99%
Parameter types
How the weights are stored.
U83.7B · 91%
Try a prompt
Base models
Model card
From the Hugging Face model README
Uploaded finetuned model
- Developed by: uberkie
- License: apache-2.0
- Finetuned from model : uberkie/qwen3-4B-self-thinking-16bit
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Mar 26, 2026
- Updated
- Jun 18, 2026