VibeThinker-3B

WeiboAI · VibeThinker

3B parameter open-weight model. Built on Qwen2.5-3B with a 64K long-context training window focused on complete reasoning trajectories; runs comfortably on consumer GPUs with 4–6 GB VRAM via Ollama or LM Studio using any of the 46 available GGUF quantizations, but is not suited for tool-calling or agentic workflows.

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHuggingFace model card (WeiboAI/VibeThinker-3B), official docs, OpenSourcesAI editorial review.

VRAM figures are empirical estimates. Actual usage varies by runtime, context length, and system configuration. Verify on your specific hardware before production use.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →