MiMo-V2-Flash
MiMo-V2-Flash is an open-weights language model from Xiaomi, released December 16, 2025. It has 310B parameters (mixture-of-experts, 10B active). The context window is 256K tokens.
We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities.
Check it against your own PC →
Can you run MiMo-V2-Flash locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: unsloth/MiMo-V2-Flash-GGUF · bartowski/XiaomiMiMo_MiMo-V2-Flash-GGUF · mradermacher/MiMo-V2-Flash-i1-GGUF · DevQuasar/XiaomiMiMo.MiMo-V2-Flash-GGUF · mradermacher/MiMo-V2-Flash-GGUF · ubergarm/MiMo-V2-Flash-GGUF
Benchmark results
Epoch AI has not published results for MiMo-V2-Flash yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: XiaomiMiMo/MiMo-V2-Flash
More from Xiaomi
MiMo V2.6 Flash MOPD · MiMo V2.6 Pro MOPD · MiMo-V2.6-Pro · MiMo-V2.6-Flash · MiMo V2.6 Pro RL · MiMo V2.6 Flash RL · MiMo-V2.5 · MiMo-V2.5-Pro