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

Libraries

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

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

pipe = pipeline("text-generation", model="XiaomiMiMo/MiMo-V2-Flash", 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-Flash", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use XiaomiMiMo/MiMo-V2-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XiaomiMiMo/MiMo-V2-Flash"
# 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-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

bwshen-mi commited on Dec 17, 2025

Commit

f25fa7e

verified ·

1 Parent(s): dd63325

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -4

README.md CHANGED Viewed

@@ -202,8 +202,6 @@ To support high-throughput RL training for large-scale MoE models, we implemente
 MiMo-V2-Flash supports FP8 mixed precision inference. We recommend using **SGLang** for optimal performance.
-Usage Recommendations: we recommend setting the sampling parameters to `temprature=0.8, top_p=0.95`.
 ### Quick Start with SGLang
 ```bash
@@ -256,8 +254,7 @@ curl -i http://localhost:9001/v1/chat/completions \
 ### Notifications
-> [!IMPORTANT]
-> In the thinking mode with multi-turn tool calls, the model returns a `reasoning_content` field alongside `tool_calls`. To continue the conversation, the user must persist all history `reasoning_content` in the `messages` array of each subsequent request.
 > [!IMPORTANT]
 > The following system prompts are **HIGHLY** recommended, please choose from English and Chinese version.
@@ -278,6 +275,22 @@ Chinese
 今天的日期：{date} {week}，你的知识截止日期是2024年12月。
 ```
 -----
 ## 7. Citation

 MiMo-V2-Flash supports FP8 mixed precision inference. We recommend using **SGLang** for optimal performance.
 ### Quick Start with SGLang
 ```bash
 ### Notifications
+#### 1. System prompt
 > [!IMPORTANT]
 > The following system prompts are **HIGHLY** recommended, please choose from English and Chinese version.
 今天的日期：{date} {week}，你的知识截止日期是2024年12月。
 ```
+#### 2. Sampling parameters
+> [!IMPORTANT]
+> Recommended sampling parameters:
+>
+> `top_p=0.95`
+>
+> `temperature=0.8` for math, writing, web-dev
+>
+> `temperature=0.3` for agentic taks (e.g., vibe-coding, tool-use)
+#### 3. Tool-use practice
+> [!IMPORTANT]
+> In the thinking mode with multi-turn tool calls, the model returns a `reasoning_content` field alongside `tool_calls`. To continue the conversation, the user must persist all history `reasoning_content` in the `messages` array of each subsequent request.
 -----
 ## 7. Citation