Local AI with MiMo V2.6 inference snap
MiMo-V2.6-Distill-Qwen-9B is a 9B multimodal 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.
Use this snap to quickly install an optimized environment for local inference with MiMo V2.6.
The snap includes the following hardware-optimized inference engines:
- cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
- nvidia-gpu: CUDA-enabled GPU acceleration
The most suitable engine is automatically selected based on the available hardware.
Install:
sudo snap install mimo-v2-6
Run:
mimo-v2-6
Some accelerators require extra drivers to be usable with this snap:
https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/
License:
The MiMo V2.6 model is provided by Xiaomi MiMo under the MIT license:
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
The licenses of all the bundled software can be found after installing the snap at
/snap/mimo-v2-6/current/usr/share/doc.