Xiaomi's MiMo-V3 gets new HySparse2 architecture: 5x prefill FLOPs cut, 4.5x smaller KV cache
teortaxesTex · x · 2026-09-23
Xiaomi's MiMo-V3 debuts the HySparse2 architecture, designed for agentic inference workloads. Versus MiMo-V2.6's Hybrid-SWA: 5.02x lower prefill FLOPs and 4.5x smaller KV cache at 1M tokens, with better MRCRv2/RULER-v2 retrieval and lower AgentPPL/LongPPL. Commenters note HySparseV2 is a more cautious cousin of V4.1, keeping full-attention backbone layers.
Related event: Xiaomi's MiMo-V3 to Adopt New HySparse2 Architecture(3 posts)→
More from Models
- Matt Shumer declares 'Anthropic has won,' calls new model incredible — mattshumer_ · 2026-09-24
- Testing the Jeb chatbot: inconsistently biased, not neutral — calibrate it like any classifier — PawarBI · 2026-09-24
- Pokemon benchmark Paradigm 3: Astra generalizes to scrambled maps and fan-made games while rivals memorize — gleech · 2026-09-24
- AI Completes Fan-Made Pokemon Brown in 10K Steps: Real Generalization or Whack-a-Mole? — gleech · 2026-09-24
- Next-gen model names surface: Opus 5.5, Fable 5.1, GPT-6 Astra — labs said to be ~2 months ahead internally — haider1 · 2026-09-24
- AI detector debate: economist argues Pangram is the only reliable tool, cites 0 FPR finding — paulnovosad · 2026-09-24