XiaomiMiMo VL
MiMo VL 7B SFT 2508
The 2508 SFT release is part of Xiaomi's updated MiMo VL pair. The update adds control over whether the model uses a visible reasoning mode.
Research release
Compare direct output with reasoning output
Practical guidance. For extraction, a direct answer can be easier to parse. For visual questions that require several deductions, compare the reasoning mode. Keep the requested answer format constant so that mode control does not hide a formatting regression.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | MiMo-VL-7B-SFT-2508 |
| Licence | MIT.MiMo-VL-7B-SFT-2508 official model card |
| Thinking control | The update documents a no_think control for direct responses.MiMo-VL-7B-SFT-2508 official model card |
| Related release | A separate RL-2508 checkpoint is published alongside SFT-2508.MiMo-VL-7B-SFT-2508 official model card |
Related models
- MiMo VL 7B RL 2508
Xiaomi · MiMo VL
An updated MiMo VL 7B reasoning model for image and video tasks with an option to disable reasoning.
Launch date not confirmedDownloadable - MiMo VL 7B SFT
Xiaomi · MiMo VL
A 7B vision-language model trained through alignment, multimodal pretraining and supervised instruction tuning.
Launch date not confirmedResearch releaseDownloadable