Autor: Jakub Rusinowski · Ostatnia aktualizacja: 10 marca 2026
Model MoE Xiaomi o ponad bilionie parametrów, pierwotnie wypuszczony anonimowo jako „Hunter Alpha” w marcu 2026, zanim ujawniono go jako MiMo-V2-Pro. Pracami kierowała Luo Fuli, była inżynierka DeepSeek. W momencie premiery był największym modelem na OpenRouter. Mocne wyniki w agentowych benchmarkach PinchBench i ClawEval przy ~42B aktywnych parametrach na token. Dostępny przez API Xiaomi oraz OpenRouter.
| Licence | What it permits | Applies to |
|---|---|---|
Custom Open-Weight | Commercial use permitted Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms. | MiMo-V2-Pro 1T+ |
| MiMo-V2-Pro 1T+ | Min 605 GB VRAM · Q4_K_M · 1,000,000 ctx · |
Install Ollama then run: ollama run
Minimum VRAM: 605 GB. For best results use Q4_K_M quantization.
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.
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.
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.
Install Ollama, then run: ollama run . This downloads MiMo-V2-Pro and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.