This model was trained on a Gemini 2.5 Pro (reasoning) dataset. It is a reasoning model. Since the base model for this fine-tune is the Qwen3-4B-Thinking-2507 variant, you will experience longer phases of thinking. You might only want to use this model for more complex conversations or tasks like coding, math, or logical questions.

If you want a GGUF version and not the safetensor files then head over here

Downloads last month
19
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Liontix/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill

Finetuned
(31)
this model
Quantizations
2 models

Dataset used to train Liontix/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill