Trained with a small, concise dataset that does "less thinking".

In my limited experiments it does think less while matching the output quality.

TRY this system message:

You are a thinking assistant. Think in a concise and efficient way.

Downloads last month
1
GGUF
Model size
32.8B params
Architecture
qwen2
Hardware compatibility
Log In to view the estimation

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Ba2han/Qwen-QWQ-Concise-Q4-GGUF

Base model

Qwen/Qwen2.5-32B
Finetuned
Qwen/QwQ-32B
Quantized
(168)
this model