Discussion

• @clementdelangue Clem on x

  This is how it's done! Who else should we ask to release weights? [image]

• @artificialanlys @artificialanlys on x

  Xiaomi's MiMo V2.5 Pro has landed at 54 in the Artificial Analysis Intelligence Index, tied with Moonshot's Kimi K2.6 - the current top open weights model. MiMo V2.5 Pro's weights are expected to be released soon, which would make MiMo V2.5 Pro the first equal open weights model …

• @_luofuli Fuli Luo on x

  Just dropped two open-source models: MiMo-V2.5-Pro (Code Agent, 1T total) and MiMo-V2.5 (Multimodal Agent, 310B total). Oh and one more thing — we're giving devs & creators 100T tokens on us. Go build something cool 🛠️ 🎁 100T Free Token Grant for Builders

• @xiaomimimo @xiaomimimo on x

  SGLang and vLLM support for the MiMo-V2.5 series is here. 🙌 Huge thanks to SGLang project from @lmsysorg and @vllm_project for moving fast and helping developers get started with MiMo-V2.5 on day zero. [image]

• @stochasticchasm @stochasticchasm on x

  interesting that the small model got 48T but the big one only got 27T. i guess a lot of that is probably just multimodal. [image]

• @eliebakouch Elie on x

  xiaomi mimo v2.5 eval card, pro is 1T total 42B active, omni (video/image/audio) is 310B total 15B active, both have 1M context support they train in FP8, 27T tokens for pro and 48T for the smaller variant. interleaved SWA with an aggressive 6:1 ratio and 128 window size, still […

• @theahmadosman Ahmad on x

  New Opensource SoTA contender enters the arena Xiaomi MiMo-V2.5 Pro - 1.02T Total Params / 42B Active Params - Base and Instruct versions Xiaomi MiMo-V2.5 - 310B Total Params / 15B Active Params - Base and Instruct versions MIT License Opensource AI just keeps getting better [ima…

• @lmsysorg @lmsysorg on x

  🎉 MiMo-V2.5 series is here, day-0 support is now live in SGLang! Two models to try: 1️⃣ MiMo-V2.5-Pro: 1.02T/42B MoE, hybrid attention, up to 1M context 2️⃣ MiMo-V2.5: full multimodal (text, image, video, audio), 310B/15B MoE, 1M context We also have day 0 support for this model …

• @xiaomimimo @xiaomimimo on x

  MiMo-V2.5 achieved Day-0 adaptation across multiple chip platforms on the first day of open source release. Huge thanks to our hardware ecosystem partners for helping make MiMo-V2.5 easier to deploy and run efficiently across more environments: @awscloud、@AMD [image]

• @teortaxestex @teortaxestex on x

  ...It wasn't an intern's joke MiMo 2.5 (not Pro): > Trained on a total of ~48T tokens using FP8 mixed precision. The context window supports up to 1M tokens. We've got another 1M class, and the largest disclosed pretrain. Congrats Xiaomi. [image]