MiMo V2.5 Pro is an open-source language model by XiaomiMiMo. Features: 1023.2b LLM, VRAM: 2.5GB, Context: 1024K, License: mit, LLM Explorer Score: 0.53.
Agent Code Conversational Custom code En Eval-results Fp8 Long-context Mimo v2 Region:us Safetensors Zh
Model Card on HF 🤗: https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro
MiMo V2.5 Pro Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MiMo V2.5 Pro Parameters and Internals
| LLM Name | MiMo V2.5 Pro |
| Repository 🤗 | https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro |
| Model Size | 1023.2b |
| Required VRAM | 2.5 GB |
| Updated | 2026-05-01 |
| Maintainer | XiaomiMiMo |
| Model Type | mimo_v2 |
| Model Files | |
| Supported Languages | en zh |
| Model Architecture | MiMoV2ForCausalLM |
| License | mit |
| Context Length | 1048576 |
| Model Max Length | 1048576 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152576 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the MiMo V2.5 Pro Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53373 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a