MiMo Models — Hardware Requirements
5 MiMo models from Xiaomi and the community, from the smallest that runs in 3.4 GB of VRAM up to 1020B parameters. Every row links to full quantization tables and GPU compatibility.
All MiMo Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| MiMo V2.6 Distill Qwen 9B | 9.4B | 3.4 GB | 262K | ||
| MiMo V2.6 Flash RL | 309B | 93.1 GB | 1049K | ||
| MiMo v2 Flash | 309.8B | 85.6 GB | 262K | ||
| MiMo V2.5 | 310.8B | 85.9 GB | 1049K | ||
| MiMo V2.6 Pro RL | 1020B | 434.0 GB | 1049K |
Frequently Asked Questions
- How much VRAM do I need to run a MiMo model?
- The smallest MiMo model, MiMo V2.6 Distill Qwen 9B, runs from 3.4 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which MiMo models can I run on a 16 GB GPU?
- 1 of 5 MiMo models fit in 16 GB of VRAM at some quantization, including MiMo V2.6 Distill Qwen 9B.
- What is the most popular MiMo model to run locally?
- MiMo V2.6 Distill Qwen 9B is the most downloaded MiMo model in local-friendly quantized formats. It runs from 3.4 GB of VRAM.