mimo-v2.6

236 Downloads Updated 2 hours ago

MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo’s 9B model for code and agent workflows

vision tools thinking 9b

ollama run mimo-v2.6

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mimo-v2.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mimo-v2.6',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mimo-v2.6',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model mimo-v2.6

OpenCode

OpenCode ollama launch opencode --model mimo-v2.6

Hermes Agent

Hermes Agent ollama launch hermes --model mimo-v2.6

OpenClaw

OpenClaw ollama launch openclaw --model mimo-v2.6

Models

Name

8 models

Size / Usage

Context

Input

mimo-v2.6:latest

6.6GB - 8.7GB · 256K context window · Text, Image · 2 hours ago

mimo-v2.6:latest

6.6GB - 8.7GB

256K

Text, Image

mimo-v2.6:9b

6.6GB - 8.7GB · 256K context window · Text, Image · 2 hours ago

mimo-v2.6:9b latest

6.6GB - 8.7GB

256K

Text, Image

Readme

MiMo-V2.6-Distill-Qwen-9B

MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo’s 9B model for code and agent workflows. Fine-tuned from Qwen3.5-9B on MiMo-generated data, it works with text and images and supports thinking and tool use.

What you can use it for

Software development: understand unfamiliar code, investigate failures, and draft fixes.
Agent workflows: work through multi-step tasks when connected to tools.
Visual coding: use screenshots or interface references to guide an implementation.
Security analysis: examine code and explain potential vulnerabilities.

With support for up to 256K tokens of context, the model can work across long files, documentation, and extended task histories.

Get started

ollama run mimo-v2.6

Evaluation

Xiaomi reports these results for MiMo-V2.6-Distill-Qwen-9B:

Benchmark	Metric	Qwen3.5-9B	MiMo-V2.6-Distill-Qwen-9B
SWE Verified	avg@3	60.0	61.1
SWE Pro	avg@3	32.0	44.6
AutomationBench v1.0.6	avg@1	5.0	30.3
Terminal Bench 2.1	avg@1	27.0	37.1
Toolathlon-Verified	avg@1	25.9	35.2

See Xiaomi’s model card and the MiMo-V2.6 technical report for the evaluation setup and more results. The model is released under the MIT license.

# MiMo-V2.6-Distill-Qwen-9B

MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo's 9B model for code and agent workflows. Fine-tuned from Qwen3.5-9B on MiMo-generated data, it works with text and images and supports thinking and tool use.

## What you can use it for

- **Software development:** understand unfamiliar code, investigate failures, and draft fixes.
- **Agent workflows:** work through multi-step tasks when connected to tools.
- **Visual coding:** use screenshots or interface references to guide an implementation.
- **Security analysis:** examine code and explain potential vulnerabilities.

With support for up to 256K tokens of context, the model can work across long files, documentation, and extended task histories.

## Get started

```sh
ollama run mimo-v2.6
```

## Evaluation

Xiaomi reports these results for MiMo-V2.6-Distill-Qwen-9B:

| Benchmark | Metric | Qwen3.5-9B | MiMo-V2.6-Distill-Qwen-9B |
| --- | --- | ---: | ---: |
| SWE Verified | avg@3 | 60.0 | 61.1 |
| SWE Pro | avg@3 | 32.0 | 44.6 |
| AutomationBench v1.0.6 | avg@1 | 5.0 | 30.3 |
| Terminal Bench 2.1 | avg@1 | 27.0 | 37.1 |
| Toolathlon-Verified | avg@1 | 25.9 | 35.2 |

See [Xiaomi's model card](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B) and the [MiMo-V2.6 technical report](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/blob/main/MiMo_V2_6_technical_report.pdf) for the evaluation setup and more results. The model is released under the MIT license.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)