Skip to content
Xiaomi

MiMo V2 Flash 309B

flagship
Xiaomi · released 2025-06-01 · text
currently routing · 4.2k rpm
131.1M tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
open
License
/ ABOUT

MiMo V2 Flash 309B is a large Mixture-of-Experts language model from Xiaomi, featuring 309 billion total parameters with efficient expert routing for high-quality text generation and reasoning. The Flash designation indicates it's optimized for fast inference relative to its total parameter count.

The model delivers strong performance on Chinese and English language tasks, with capabilities spanning reasoning, coding, mathematics, and creative generation. It supports a substantial context window and handles complex multi-turn conversations and long-document processing effectively.

MiMo V2 Flash 309B represents Xiaomi's entry into the frontier model space, offering competitive quality through an efficient MoE architecture designed for production deployment.

BENCHMARKS Artificial Analysis Index
Intelligence 30

Providers for MiMo V2 Flash 309B

0 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d