Qwen3 4B Thinking 2507 x Kimi k2 thinking

This model was trained on 1000 examples from MoonshotAI's Kimi k2 thinking.

  • Developed by: TeichAI
  • License: apache-2.0
  • Finetuned from model : unsloth/Qwen3-4B-Thinking-2507

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

Downloads last month
16
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
Input a message to start chatting with TeichAI/Qwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill.

Model tree for TeichAI/Qwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill

Finetuned
(105)
this model
Merges
9 models
Quantizations
4 models