Mirrored from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
All models by XiaomiMiMo →MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity. We release this SFT checkpoint as a starting point for open research in agentic reinforcement learning.
Results for the released SFT checkpoint, as reported in the MiMo-V2.6 technical report.
† Internal evaluation sets.
The weighted SFT data mixture contains 77.4B total tokens, including 27.2B loss-bearing tokens.
For text generation, use a recent SGLang build with Qwen3.5 support. The checkpoint includes its tokenizer and MiMo v2.6 chat template.
Query the endpoint with thinking explicitly enabled:
sglang serve \ --model-path XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B \ --reasoning-parser mimo \ --host 0.0.0.0 \ --port 30000from openai import OpenAI
client = OpenAI( base_url="http://localhost:30000/v1", api_key="EMPTY",)
response = client.chat.completions.create( model="XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B", messages=[ {"role": "user", "content": "What is 15% of 240?"} ], max_tokens=2048, extra_body={"chat_template_kwargs": {"enable_thinking": True}},)
message = response.choices[0].messageprint("Thinking:", getattr(message, "reasoning_content", "") or "")print("Answer:", message.content or "")@misc{mimo2026v26, title={MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement}, author={{Xiaomi MiMo Team}}, year={2026}, howpublished={\url{https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL}},}