MiMo-V2.6-Pro-MOPD
MiMo-V2.6-Pro-MOPD is a multimodal sparse MoE model with 1.02T total parameters, 42B activated parameters, and a context length of up to 1M tokens. Its MOPD training combines domain-specialized teachers and is intended to reduce repeated tool calls in agentic settings.
What it does
A person can use it for multimodal tasks, tool-using agents, long-horizon game development, scientific research, and embodied intelligence.
- Availability
- Available on Hugging Face and ModelScope; also listed as available in AI Studio, MiMo Code, Xiaomi MiMo Desktop, Xiaomi MiMo Open Platform API, and OpenRouter.
- Pricing model
- Not established
- Deployment
- SGLang and vLLM deployment instructions are provided.
- Privacy
- Not established
- Licence
- The applicable model licence is not named; the page lists use restrictions.
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model has a stated context length of 1M tokens. [1]
Following the release of MiMo-V2.6, tool-call repetition emerged as one of the most noticeable issues in agentic settings: the model would sometimes issue the same or highly similar tool calls repeatedly, consuming time and context without making progress.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Its listed modalities are text, image, video, and audio. [1]
- **Modalities**: Text, Image, Video, Audio
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The checkpoint is described as mitigating repeated or highly similar tool calls. [1]
> An easy-to-overlook failure mode in which the model keeps issuing the same or highly similar tool calls, appearing busy while making no progress.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The checkpoint is downloadable from Hugging Face and ModelScope. [1]
- The page provides serving instructions for SGLang and vLLM. [1]
- The listed use restrictions include military applications and certain malicious cyber activities. [1]
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-MOPD
Retrieved 2026-10-29 00:34 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-29 00:34 UTC | material change | capability, availability, deployment | Current |
| 2 | 2026-09-29 07:16 UTC | material change | capability, access, availability, deployment | Current |
| 1 | 2026-09-28 08:08 UTC | publication | None | Current |
In briefs
1- ElevenLabs introduces two text-to-speech models Daily brief 2026-09-28
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.