qingy2024/Refined-Gem-4B-Thinking
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Dec 15, 2025License:apache-2.0Architecture:Transformer Open Weights Warm

Refined-Gem-4B-Thinking by qingy2024 is a 4 billion parameter Qwen3-based causal language model, fine-tuned on outputs from Gemini 2.5 Flash and Gemini 3.0 Preview. This model is specifically designed for enhanced reasoning and 'thinking' capabilities, generating internal thought processes before producing a final answer. It supports a context length of 40960 tokens, making it suitable for complex problem-solving and detailed response generation.

Loading preview...