Qwen3 4B Thinking 2507 - MiMo V2 Flash Distill

This model was trained on a reasoning dataset of MiMo V2 Flash.

• 🧬 Datasets:

  • TeichAI/MiMo-V2-Flash-2300x

• 🏗 Base Model:

  • unsloth/Qwen3-4B-Thinking-2507

• ⚡ Use cases:

  • Coding
  • Science
  • Chat
  • Deep Research

• ∑ Stats (Dataset)

  • Costs: $ 0.00 (USD)
  • Total tokens (input + output): 7.36 M

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

An Ollama Modelfile is included for easy deployment.