VibeThinker-3B: 3B稠密推理模型基于Qwen2.5-Coder-3B发布
VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline
3B参数就能比肩DeepSeek V3.2和Kimi K2.5，基于Qwen2.5-Coder-3B开源，适合资源受限场景的推理任务。
VibeThinker-3B是一个3B参数的MIT许可证推理模型，基于Qwen2.5-Coder-3B构建。
该模型采用Spectrum-to-Signal后训练流水线。在可验证基准上，它匹配了DeepSeek V3.
2和Kimi K2.5的性能。
VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline
VibeThinker-3B, a 3B MIT-licensed reasoning model matching DeepSeek V3.2 and Kimi K2.5 on verifiable benchmarks. The post VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline appeared first on MarkTechPost .
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include VibeThinker-3B, Qwen2.5-Coder-3B, DeepSeek V3.2, Kimi K2.5.
Primary source verification: published directly by marktechpost with first-party authority. Cross-source corroboration: 3 independent sources have covered this development (including Sebastian Raschka, arXiv: DeepSeek), confirming industry-wide signal strength.
