Instructions to use XiaomiMiMo/MiMo-V2.6-Pro-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="XiaomiMiMo/MiMo-V2.6-Pro-RL", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XiaomiMiMo/MiMo-V2.6-Pro-RL", trust_remote_code=True, device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XiaomiMiMo/MiMo-V2.6-Pro-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XiaomiMiMo/MiMo-V2.6-Pro-RL

SGLang

How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "XiaomiMiMo/MiMo-V2.6-Pro-RL" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "XiaomiMiMo/MiMo-V2.6-Pro-RL" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XiaomiMiMo/MiMo-V2.6-Pro-RL with Docker Model Runner:
```
docker model run hf.co/XiaomiMiMo/MiMo-V2.6-Pro-RL
```

Question about reproducibility of benchmarks (Table 3 of Technical Report)? | 关于技术报告表 3 中基准测试可复现性的问题

by pandemo - opened 10 days ago

Discussion

pandemo

10 days ago

•

edited 10 days ago

Hi MiMo team, thank you so much for open-sourcing such impressive models and sharing your research!

A quick question about reproducing the Table 3 results in the technical report: which agentic harnesses(eg Claude Code, Codex...etc) were used for the Code Agent, General Agent, and Cybersecurity benchmarks? Were MiMo Code or mimoagent used for any of them?

I couldn’t find a benchmark-to-harness mapping /methodology in the report. Any details you can share would be deeply appreciated by the research community🙏!

MiMo 团队好！非常感谢你们开源如此出色的模型，并分享研究成果！

想请教一个关于复现技术报告表 3 结果的问题：Code Agent、General Agent 和 Cybersecurity 这几类基准测试分别使用了哪些智能体运行框架（例如 Claude Code、Codex 等）？其中是否有测试使用了 MiMo Code 或 mimoagent？

我在报告中没有找到各项基准测试与所用框架的对应关系或具体评测方法。如果能分享一些相关信息，研究社区会非常感激🙏

CoderX1997

7 days ago

Suggestion: try a bunch of them, and if they don't work, it was something with either the prompting or an agent change.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment