CONSONANCE.for your information
Monday, 5 October 2026frenvi

Being discussed

01 — inference 3 VOICES

Xiaomi releases MiMo-V2.6 models with day-one vLLM support

Xiaomi introduced the MiMo-V2.6 mixture-of-experts models combining text, image, video, and audio, featuring a Pro version with 1.02T total parameters (42B active) and a Flash version with 309B total parameters (15B active). Both sizes received day-one vLLM support with a 1-million token context.

3 independent accounts 20 posts 1 labs 3,635 interactions
vllm
@GithubProjects their topics on X ↗
@teortaxesTex their topics on X ↗
@vllm_project their topics on X ↗
@PyTorch their topics on X ↗
@XiaomiMiMo their topics on X ↗
@aiDotEngineer their topics on X ↗
@fraserpricee their topics on X ↗
@inferact their topics on X ↗
↑