Language modelOpen weights
MiMo V2.6 Distill Qwen 9B
Xiaomi
- Released
- September 22, 2026
- Data date
- September 22, 2026
MiMo V2.6 Distill Qwen 9B is Xiaomi’s local 9B SFT checkpoint fine-tuned from Qwen 3.5 9B on MiMo-generated data. It accepts text and images and is much smaller than the full V2.6 Pro and Flash RL models. The checkpoint is aimed less at a hosted API and more at research and custom inference.
Xiaomi describes it as a starting point for research into agentic reinforcement learning. The SFT starting point anchors the released RL resources and positions the checkpoint as a research component within the V2.6 family.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | 9B agentic checkpointSource |
| Access | Local executionSource |
| Checkpoint | MiMo-V2.6-Distill-Qwen-9B, MIT licenseSource |
| Base model | SFT fine-tuned from Qwen3.5-9BSource |
| Parameters | 9BSource |
| Modalities | Text and imageSource |
| Provider availability | No deployed Hugging Face Inference ProviderSource |
Popularity
0 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | Xiaomi MiMo V2.6 announcement (retrieved September 22, 2026) · Xiaomi MiMo V2.6 announcement · Editorial description reviewed October 2, 2026 |
| Additional source | MiMo V2.6 Distill Qwen 9B model card (retrieved September 22, 2026) · MiMo V2.6 Distill Qwen 9B model card · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |