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

Libraries

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XiaomiMiMo/MiMo-V2.6-Flash-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-Flash-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-Flash-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use XiaomiMiMo/MiMo-V2.6-Flash-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-Flash-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-Flash-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-Flash-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-Flash-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

MiMo native parser support?

by Lanchou - opened 4 days ago

Discussion

Lanchou

4 days ago

Very glad to see our Xiaomi guys coming back with the V2.6 - the benchmarks look amazing! I see you also have an xring AI hub on the roadmap (feels like a DGX spark for home). The V2.6 flash seems to fit very well in that device, which makes a lot of sense.

However, I didn't see a native parser in the image (seems to default to a Qwen 3 one), will you provide it? This is kind of important as I see reports of the self-host people complaining about the V 2.6 thinking leaks to the contents after tool calls (looks like jabber), e.g. this one:
https://github.com/tonyd2wild/MiMo-V2.6-Flash-DGX-Spark-Recipe/issues/1

I recall people talking about a similar issue a while ago when MiMo 2.5 was out. It didn't last long, though, because MiMo wasn't really that state-of-art back then - and we had DeepSeek V4 coming out. Hope that it works out this time!

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