MiMo-V2-Pro — local AI model by Xiaomi
Written by Jakub Rusinowski · Last updated
Xiaomi's 1T+ MoE model originally launched anonymously as 'Hunter Alpha' in March 2026 before being revealed as MiMo-V2-Pro. Led by ex-DeepSeek engineer Luo Fuli. Was the largest model on OpenRouter at launch. Strong on PinchBench and ClawEval agentic benchmarks with ~42B active parameters per token. Available via API through Xiaomi and OpenRouter.
Variants
The smallest MiMo-V2-Pro variant needs about 605 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| MiMo-V2-Pro 1T+ → 1T+ | ~604.6 GB | 1,000,000 | ollama run mimo-v2-pro |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run MiMo-V2-Pro locally
Install Ollama, then pull the tag.
ollama run mimo-v2-proPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: MiMo-V2-Pro 1T+Can I run MiMo-V2-Pro on my GPU?
MiMo-V2-Pro — frequently asked questions
How much VRAM does MiMo-V2-Pro need?
MiMo-V2-Pro needs about 605 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: MiMo-V2-Pro 1T+ (605 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run MiMo-V2-Pro on an RTX 4090 (24 GB)?
MiMo-V2-Pro's smallest variant needs about 605 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for MiMo-V2-Pro?
Q4_K_M is the best balance of quality and VRAM for MiMo-V2-Pro in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run MiMo-V2-Pro with Ollama?
MiMo-V2-Pro has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.