Unverified50% confidenceEventExact time
The Peano AI team ran full-parameter reinforcement learning for Xiaomi's 310B-parameter MiMo-V2.6 model on a cluster of more than 1,000 TPUs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedXiaomi has publicly released MiMo-V2.6's model weights, technical report, reinforcement learning (RL) environment, and training code.69% similarUnverifiedThe team trained a 27B-parameter LynnReal-Omni-Flash version that uses three-step generation to reduce inference overhead through model acceleration, decoding acceleration, and a lightweight VAE decoder.66% similarUnverifiedXiaomi launched MiMo-V2.6 on Product Hunt, an open-source omnimodal model family designed for long-horizon agent tasks.64% similarUnverifiedMiMo VL Pro总参数量达1T，激活参数42B，支持100万上下文窗口，采用混合专家（MoE）架构62% similarUnverifiedThis benchmark was conducted on four model families — Gemma, Qwen, Kimi, and MiniMax — using AMD Instinct MI300X and MI355X hardware.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945481API
curl https://kongchang.com/api/v1/knowledge/claims/945481MCP
get_claim(id=945481)