TeichAI/Qwen3-32B-Kimi-K2-Thinking-Distill

Qwen3 32B - Kimi K2 Thinking Distill

This model was trained on 1000 high reasoning examples from Kimi-K2-Thinking.

• 🧬 Datasets:

  • TeichAI/kimi-k2-thinking-1000x

• 🏗 Base Model:

  • unsloth/Qwen3-32B

• ⚡ Use cases:

  • Coding
  • Math
  • Chat
  • Deep Research

---

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.