When was MiMo-V2.6-Flash released?

MiMo-V2.6-Flash was released on September 22, 2026 by Xiaomi. This is the official MiMo-V2.6-Flash release date tracked on LLM Stats.

How big is MiMo-V2.6-Flash?

MiMo-V2.6-Flash has 309 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created MiMo-V2.6-Flash?

MiMo-V2.6-Flash was created by Xiaomi.

What is the license for MiMo-V2.6-Flash?

MiMo-V2.6-Flash is released under the MIT license. This is an open-source / open-weight license that permits self-hosting.

Is MiMo-V2.6-Flash multimodal?

Yes, MiMo-V2.6-Flash is multimodal and can accept both text and images as input.

Where is the MiMo-V2.6-Flash paper or technical report?

MiMo-V2.6-Flash has a paper or technical report available at https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL/blob/main/MiMo_V2_6_technical_report.pdf. Use that source for architecture, training, release and evaluation details.

What models should I compare MiMo-V2.6-Flash against?

Common MiMo-V2.6-Flash comparisons include MiMo-V2.6-Flash vs Claude Mythos Preview, MiMo-V2.6-Flash vs Atria Dawn Preview, MiMo-V2.6-Flash vs Qwen3.8 Max. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.

MiMo-V2.6-Flash Benchmarks, Pricing & Context Window

Name: MiMo-V2.6-Flash
Author: Xiaomi

MiMo-V2.6-Flash: Benchmarks, Pricing & Context Window

MiMo-V2.6-Flash is a language model from Xiaomi, released in September 2026, with multimodal input.

MiMo-V2.6-Flash is Xiaomi's MIT-licensed omnimodal sparse Mixture-of-Experts model with 309B total parameters and 15B active parameters. It supports text, image, video, and audio understanding with a 1,048,576-token context window and text

MiMo-V2.6-Flash benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for MiMo-V2.6-Flash across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How MiMo-V2.6-Flash holds up as conversations get longer.

Quality Tracker

MiMo-V2.6-Flash Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Tue Sep 22 2026

Notice missing or incorrect data?

MiMo-V2.6-Flash model size

MiMo-V2.6-Flash has 309 billion parameters. See how it compares to other models in the same parameter range.

Parameters

309BMoE

Frontier (200B+)

309B

1B7B70B405B

Try now

huggle

MiMo-V2.6-Flashin Huggle

Make it with
MiMo-V2.6-Flash.

MiMo-V2.6-Flash latency

MiMo-V2.6-Flash time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

MiMo-V2.6-Flash examples

Recent arena outputs from MiMo-V2.6-Flash, picked from the highest-ranked matchups.

MiMo-V2.6-Flash license

MiMo-V2.6-Flash is released under the MIT license, which permits commercial use, has 309.0B parameters.

License: MIT; Commercial use allowed
Parameters: 309.0B

MIT License - allows commercial use

MiMo-V2.6-Flash resources

Official sources for MiMo-V2.6-Flash: provider documentation, official playground, paper or system card, official launch post, model weights.

MiMo-V2.6-Flash vs other models

The most-compared alternatives to MiMo-V2.6-Flash are Claude Mythos Preview, Atria Dawn Preview, Qwen3.8 Max. Open any pair side-by-side for benchmarks, pricing, context, and latency.