MMLForge Search models, datasets, tasks… Start free
Home › Models › Text Generation › Qwen/Qwen3-4B-Thinking-2507
Q

Qwen/Qwen3-4B-Thinking-2507

Text Generation·Qwen· 581.4K· 600
transformers apache-2.0 4.0B params arxiv:2505.09388license:apache-2.0deploy:azureregion:us

Over the past three months, we have continued to scale the thinking capability of Qwen3-4B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-4B-Thinking-2507, featuring the following key enhancements:

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull Qwen/Qwen3-4B-Thinking-2507

Model details

Task
Text Generation
Provider
Qwen
Framework
transformers
Parameters
4.0B
Size
7.5 GB
License
apache-2.0
Downloads
581.4K
Likes
600
Paper
arXiv:2505.09388
Updated
2025-08-06

About Qwen/Qwen3-4B-Thinking-2507

Over the past three months, we have continued to scale the thinking capability of Qwen3-4B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-4B-Thinking-2507, featuring the following key enhancements:

Related Text Generation

Q Qwen/Qwen3-0.6B Text Generation ·751.6M params 27.8M 1.4K 🤗 HF Q Qwen/Qwen3-4B Text Generation ·4.0B params 16.4M 641 🤗 HF G openai-community/gpt2 Text Generation ·137.0M params 13.3M 3.3K 🤗 HF Q Qwen/Qwen3-8B Text Generation ·8.2B params 13.0M 1.2K 🤗 HF Q Qwen/Qwen2.5-7B-Instruct Text Generation ·7.6B params 12.8M 1.4K 🤗 HF O facebook/opt-125m Text Generation 12.3M 267 🤗 HF