MiMo V2.6

Choose the size and format you want to run. Compare each version’s hardware fit, model scores, and setup guides in one place.

TextCodingAgentsImages

3versions to explore

0published guides

Compare versions

PERSONALIZE THE COMPARISONWhich machine will you use?

Save your hardware to compare which versions can run on your machine.

Add my hardware

FIND YOUR VERSION

Compare versions

Scores and requirements stay with each version.

9.41BText

MiMo V2.6 Distill Qwen 9B

MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model from Xiaomi MiMo, created by supervised fine-tuning Qwen/Qwen3.5-9B on MiMo-generated data. It is released under the MIT license and covers coding, general-purpose agent tasks, visual coding, and cybersecurity. The model card describes it as an SFT checkpoint intended as a starting point for open research in agentic reinforcement learning. It supports image-text-to-text input and includes safetensors and code tags. Reported evaluation results show improvements over Qwen3.5-9B on benchmarks such as SWE Verified, SWE Pro, Terminal Bench 2.1, and Toolathlon-Verified. The training data mixture contains 77.4B total tokens, of which 27.2B are loss-bearing. The checkpoint includes its tokenizer and MiMo v2.6 chat template, and a quickstart example is provided using SGLang with an OpenAI-compatible endpoint; thinking can be enabled via chat template kwargs.

Model size: 9.41B
Format: Published weights

Freshness 91 out of 100. Repository age: 24 days old, Sep 21, 2026. Measures age, not quality.

Popularity 62 out of 100. 25,582 downloads in 30 days; 649 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

Explore this version Model source

310.76BText

MiMo V2.6 Flash RL

MiMo V2.6 Flash RL is a text-generation model from XiaomiMiMo released under the MIT license. Its official model card describes it as the efficiency-balanced checkpoint of the MiMo-V2.6 series, built to scale reinforcement learning toward self-improvement. The card lists native omnimodal support for text, image, video, and audio, long-context capabilities stated as 1M tokens, and a mixed RL training approach covering coding, general agents, visual, and cybersecurity domains. It also describes groupwise agentic grading and multi-prefix multi-teacher on-policy distillation. The repository tags include safetensors and text-generation.

Model size: 310.76B
Context: 1,048,576

Freshness 91 out of 100. Repository age: 24 days old, Sep 21, 2026. Measures age, not quality.

Popularity 67 out of 100. 84,797 downloads in 30 days; 557 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

Explore this version Model source

1024.22BText

MiMo V2.6 Pro RL

MiMo V2.6 Pro RL is the flagship checkpoint of the MiMo-V2.6 series, released under the MIT license and intended for text-generation and multimodal use. Its model card describes scaling reinforcement learning toward self-improvement and lists native omnimodal support (text, image, video, audio), long-context handling up to 1M tokens, mixed RL across coding, general agents, visual, and cybersecurity, and training methods including GRPO, groupwise agentic grading, aligned RL, and MOPD2. The repository tags include safetensors and text-generation.

Model size: 1024.22B
Context: 1,048,576

Freshness 91 out of 100. Repository age: 24 days old, Sep 21, 2026. Measures age, not quality.

Popularity 69 out of 100. 99,548 downloads in 30 days; 728 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

Explore this version Model source