Local LLM model page

MiMo-V2.5-Pro (1.02T MoE)

Xiaomi MiMo flagship MoE for demanding agentic, software engineering and long-horizon tasks. 1M-token context, FP8, strong instruction following. MIT licensed.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
1.02T (42B active)
Minimum RAM
1024 GB
Model size
600 GB
Quantization
FP8

Can MiMo-V2.5-Pro (1.02T MoE) run locally?

MiMo-V2.5-Pro (1.02T MoE) is best suited for server-grade or multi-GPU systems. LocalClaw recommends FP8 as the default quantization, with at least 1024 GB RAM.

Search term for LM Studio or compatible runtimes: mimo-v2.5-pro

Hugging Face repository: XiaomiMiMo/MiMo-V2.5-Pro

chatcodereasoningqualityagenticlong-contextgeneral

Strengths

  • Xiaomi MiMo flagship MoE for demanding agentic, software engineering and long-horizon tasks. 1M-token context, FP8, strong instruction following. MIT licensed.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • code
  • reasoning
  • quality
  • agentic
  • long-context
  • general

Benchmarks

Speed: 2/10

Quality: 10/10

Coding: 9/10

Reasoning: 10/10

Technical details

Developer: mimo

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2026-05