MiMo V2.6 Flash
9344°
Run this model
Offers / Ads
Xiaomi | 1,050,000 token context | $0.14/M input, $0.28/M output. MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.
Guides for this model
How to Install Ollama and Run a Local AI (Windows, Mac, Linux)
Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs
Best local LLM by use case (October 2026): the right open model for every job
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
How much VRAM do I actually need for local AI?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
MiMo-V2.6-Flash is Xiaomi's efficiency-balanced open-weights model from the MiMo-V2.6 series: a sparse 309B-parameter MoE that activates only 15B per token, with a 1-million-token context and native support for text, image, video and audio. Its training method scales reinforcement learning across coding, agents, visual and cybersecurity tasks in a single mixed run, so capabilities transfer across agent harnesses rather than staying siloed. At $0.14 per million input tokens it sits well below most frontier-class multimodal models.
Known for
- Omnimodal in one model: text, image, video and audio natively
- 1-million-token context handles long repos, tool traces and multi-session runs
- Single mixed RL run transfers strategies across unseen agent harnesses
- 15B activated parameters keeps inference lean despite 309B total weights
- Open weights available on Hugging Face for self-hosting
Watch out for
- 309B total parameters means self-hosting demands serious hardware; check VRAM before committing.
- Licence terms are not detailed in what Xiaomi has published; verify before commercial deployment.
- Flash is the efficiency checkpoint; the Pro variant exists if you need the ceiling, not the price.
Prompts to try
Multi-file refactor agent
You are working in a Python monorepo. The auth module uses a global mutable config dict passed by reference across six files. Propose a concrete refactor plan: identify the risky call sites, suggest a replacement pattern using a typed dataclass, and write the updated version of the core auth.py file with the new pattern in place.
Vision: diagram to code
I am attaching a screenshot of a database entity-relationship diagram. Read the entities, their attributes and the relationships shown, then write the SQLAlchemy ORM models that match it exactly, including foreign keys and any junction tables implied by many-to-many relationships.
Long-context repo audit
I am pasting the full contents of a Node.js REST API codebase below. Read every file, then produce a security audit: list each endpoint, the authentication it applies, any input validation gaps, and any dependency versions with known CVEs. Rank findings by severity.
Compare with
- MiMo-V2.6-Pro-UltraSpeedAPI-only model1,048,576 token context · $4.35/M input, $8.70/M output
- MiMo-V2.5Open-weights model1,050,000 token context · $0.14/M input, $0.28/M output
- MiMo-V2.6-ProOpen-weights model1,050,000 token context · $0.43/M input, $0.87/M output
- MiMo-V2.5-ProOpen-weights model1,050,000 token context · $0.43/M input, $0.87/M output
More text models from xiaomi
Questions people ask
- Are the weights open and can I run MiMo-V2.6-Flash locally?
- Yes, the weights are open and hosted on Hugging Face under the repository XiaomiMiMo/MiMo-V2.6-Flash-RL. Running it locally is possible but the 309B total parameter count means you will need substantial hardware; only 15B parameters are activated per token, which helps inference cost but does not shrink the model on disk.
- What does MiMo-V2.6-Flash cost and what is its context window?
- Via Xiaomi's API it is priced at $0.14 per million input tokens and $0.28 per million output tokens, with a 1-million-token context window.
- How does Flash differ from MiMo-V2.6-Pro?
- Flash is the efficiency-balanced checkpoint in the series, trading some ceiling performance for lower inference cost; Pro is the higher-capability variant. Both share the same architecture and training approach.
Captain's verdictA genuinely cheap entry into million-token omnimodal agentic territory, and the open weights make it worth serious consideration if your hardware can handle it.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #4 Hottest Text / LLM model · #4 Hottest Text / LLM text model
Not this creator?
Get your own badge
MiMo V2.6 Flash Popularity Trend
Heat score since 21 Sep 2026
Heat score
9,344°
This week
▲
43.2%
9,297° then, 9,344° now
This month
n/a
Wasn't released/tracked
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,956°
OpenRouter tokens
32,884,504,724,760 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 3,288,450 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
+388°
Adoption rate
About 151,030 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 9,344°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.3,288,450 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,956°8,956°running total
- 3Add the adoption rate.About 151,030 downloads a day right now, measured between two readings, at a quarter of the weight.+388°9,344°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.9,344°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
MiMo V2.6 Flash is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153