@TeksEdge: Exciting News! VibeThinkiner-3B is here! Okay, localmaxxers get ready to test!! Why? The reasoning claims for a 3B mode…

X AI KOLs Following Models

Summary

Weibo AI releases VibeThinker-3B, a 3B parameter open-source reasoning model with MIT license, achieving competitive results on math, coding, and STEM reasoning benchmarks.

Exciting News! VibeThinkiner-3B is here! Okay, localmaxxers get ready to test!! Why? The reasoning claims for a 3B model are SOTA-level. Can run on many PC's with modest dedicated graphics. 3B reasoning model from Weibo AI Strong on math, coding & STEM reasoning MIT license (fully open source) Available now on Hugging Face: WeiboAI/VibeThinker-3B Claims competitive results with much larger models on verifiable reasoning benchmarks.
Original Article
View Cached Full Text

Cached at: 06/17/26, 03:57 PM

Exciting News! VibeThinkiner-3B is here! Okay, localmaxxers get ready to test!! Why? The reasoning claims for a 3B model are SOTA-level. Can run on many PC’s with modest dedicated graphics.

3B reasoning model from Weibo AI Strong on math, coding & STEM reasoning MIT license (fully open source) Available now on Hugging Face: WeiboAI/VibeThinker-3B

Claims competitive results with much larger models on verifiable reasoning benchmarks.

ModelScope (@ModelScope2022): Meet VibeThinker-3B, a 3B reasoning model from Weibo AI focused on math, coding, and STEM reasoning. MIT license. 🚀

At 3B parameters, it matches models like DeepSeek V3.2 (671B), Kimi K2.5 (1T), and GLM-5 (744B) on IMO-AnswerBench. 96.1% acceptance rate on unseen LeetCode

Similar Articles

WeiboAI/VibeThinker-3B

Hugging Face Models Trending

VibeThinker-3B is a 3B-parameter model that achieves frontier-level reasoning performance on math, coding, and STEM benchmarks by optimizing the Spectrum-to-Signal Principle (SSP) post-training pipeline, reaching performance comparable to much larger models.