Xiaomi MiMo·MiMo

MiMo-7B-RL

Xiaomi’s first open reasoning model, exploring the full pretraining-to-RL path at 7B scale.

LegacyReasoningCodingOpen weights

MODEL NUMBER122

Specifications

Only published specifications are shown.

Total parameters

Architecture

Dense

Input modalities

Text

Output modalities

Text

Open weights

Yes

License

Apache-2.0

Status

Legacy

Xiaomi’s first open reasoning model, exploring the full pretraining-to-RL path at 7B scale.

ReasoningCodingReinforcement learning

2025-04-30Open weights

Xiaomi released MiMo-7B-RL.

Select a card to view the related model.