MiMo-V2.5 Pro
MiMo-V2.5-Pro is Xiaomi’s open-source mixture-of-experts language model intended for demanding agent workflows, complex software engineering, and tasks requiring many steps over an extended sequence. Summary written by AI Index from Xiaomi’s own pages.
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
2 offerings · prices as listed| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard no longer listed since Oct 28, 2026 | ¥3.00 | ¥0.025 | ¥6.00 |
Prices from Xiaomi MiMo: pay-as-you-go pricing (opens in a new tab) (checked Oct 19, 2026)
| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard no longer listed since Oct 28, 2026 | $0.435 | $0.0036 | $0.87 |
Prices from Xiaomi MiMo: pay-as-you-go pricing (opens in a new tab) (checked Oct 19, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Knowledge cutoff
- Dec 2024
- Family
- mimo-pro
- Model ID
Not stated on Xiaomi’s pages: max input, reasoning efforts, max thinking budget, built-in tools, licence, aliases.
Run locally
Weights: XiaomiMiMo/MiMo-V2.5-Pro- Parameters 1.02T
- Active 42B · 384 experts, 8 per token
- Native precision BF16
- Layers 70
- KV cache per token 420 KB
- Config positions 1024K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 534.8 GB (weights 506.2 + KV cache 3.3 + overhead 25.3)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 962.4 GB | ≈ 1013.8 | ✕Doesn’t fit | — |
| Q8_0 | 1012.5 GB | ≈ 1066.4 | ✕Doesn’t fit | — |
| FP8 | 952.9 GB | ≈ 1003.8 | ✕Doesn’t fit | — |
| Q6_K | 782.6 GB | ≈ 825.0 | ✕Doesn’t fit | — |
| Q5_K_M | 677.8 GB | ≈ 714.9 | ✕Doesn’t fit | — |
| Q5_0 | 655.1 GB | ≈ 691.2 | ✕Doesn’t fit | — |
| Q4_K_M | 578.9 GB | ≈ 611.1 | ✕Doesn’t fit | — |
| Q4_0 | 536.0 GB | ≈ 566.1 | ✕Doesn’t fit | — |
| IQ4_XS | 506.2 GB | ≈ 534.8 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 465.7 GB | ≈ 492.3 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 364.5 GB | ≈ 386.0 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 357.3 GB | ≈ 378.5 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 245.4 GB | ≈ 260.9 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed machine; about 9 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- LMArena Text 1,467
#36 of 163 listed models · CI 1,463–1,470 · 76,826 votes
- EQ-Bench 4 1,198
#18 of 31 listed models · CI 1,185–1,213
- EQ-Bench Creative Writing v3 1,493
#54 of 95 listed models
- EQ-Bench Longform Writing 73.7
#30 of 93 listed models
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Nov 8, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 24 – 28, 2026
- changes we made
News
All news →- Oct 21, 2026Retirement Xiaomi retires MiMo-V2.5 and MiMo-V2.5 Pro MiMo-V2.5 and MiMo-V2.5 Pro are now retired.
Changes
All changes →- Available → Retired on Xiaomi MiMo API
- Available → Retired on Xiaomi MiMo API, China
- Deprecated → Retired
- New language model
Sources
- Xiaomi MiMo: models (opens in a new tab) mimo.mi.com · checked Oct 17, 2026
- Xiaomi MiMo: model updates (opens in a new tab) mimo.mi.com · checked Nov 6, 2026
- XiaomiMiMo/MiMo-V2.5-Pro model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- Xiaomi MiMo: pay-as-you-go pricing (opens in a new tab) mimo.mi.com · checked Oct 19, 2026
- Xiaomi MiMo Home (opens in a new tab) mimo.mi.com · checked Oct 20, 2026
- XiaomiMiMo/MiMo-V2.5-Pro model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- XiaomiMiMo/MiMo-V2.5-Pro model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- XiaomiMiMo/MiMo-V2.5-Pro files (opens in a new tab) huggingface.co · checked Nov 4, 2026
- XiaomiMiMo/MiMo-V2.5-Pro config.json (opens in a new tab) huggingface.co · checked Nov 8, 2026
- XiaomiMiMo/MiMo-V2.5-Pro README.md (opens in a new tab) huggingface.co · checked Nov 6, 2026
- Xiaomi MiMo: model deprecation (opens in a new tab) mimo.mi.com · checked Nov 6, 2026
Xiaomi · China · mimo.xiaomi.com
Related models
Snapshots, the same family and other models from this provider