Instructions to use miromind-ai/MiroThinker-v1.0-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use miromind-ai/MiroThinker-v1.0-8B with Transformers:

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

pipe = pipeline("text-generation", model="miromind-ai/MiroThinker-v1.0-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("miromind-ai/MiroThinker-v1.0-8B")
model = AutoModelForCausalLM.from_pretrained("miromind-ai/MiroThinker-v1.0-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use miromind-ai/MiroThinker-v1.0-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miromind-ai/MiroThinker-v1.0-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "miromind-ai/MiroThinker-v1.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/miromind-ai/MiroThinker-v1.0-8B

SGLang

How to use miromind-ai/MiroThinker-v1.0-8B 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 "miromind-ai/MiroThinker-v1.0-8B" \
    --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": "miromind-ai/MiroThinker-v1.0-8B",
		"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 "miromind-ai/MiroThinker-v1.0-8B" \
        --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": "miromind-ai/MiroThinker-v1.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use miromind-ai/MiroThinker-v1.0-8B with Docker Model Runner:
```
docker model run hf.co/miromind-ai/MiroThinker-v1.0-8B
```

MiroThinker-v1.0-8B

Commit History

Update README.md

a2fe78c
verified

YuntaoChen commited on Jan 16

Update README.md

6494be9
verified

ZhenhangHuang commited on Jan 16

Update README.md

82c8cf7
verified

Jenny Chen commited on Dec 1, 2025

Update README.md

af20003
verified

Jenny Chen commited on Nov 19, 2025

Update README.md

ab7a296
verified

Jenny Chen commited on Nov 18, 2025

Update README.md

00f50ea
verified

Jenny Chen commited on Nov 18, 2025