Instructions to use open-thoughts/OpenThinker3-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-thoughts/OpenThinker3-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="open-thoughts/OpenThinker3-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("open-thoughts/OpenThinker3-1.5B")
model = AutoModelForCausalLM.from_pretrained("open-thoughts/OpenThinker3-1.5B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use open-thoughts/OpenThinker3-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-thoughts/OpenThinker3-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-thoughts/OpenThinker3-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/open-thoughts/OpenThinker3-1.5B

SGLang

How to use open-thoughts/OpenThinker3-1.5B 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 "open-thoughts/OpenThinker3-1.5B" \
    --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": "open-thoughts/OpenThinker3-1.5B",
		"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 "open-thoughts/OpenThinker3-1.5B" \
        --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": "open-thoughts/OpenThinker3-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use open-thoughts/OpenThinker3-1.5B with Docker Model Runner:
```
docker model run hf.co/open-thoughts/OpenThinker3-1.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

paper | dataset | model

We have released a paper for OpenThoughts! See our paper here.

OpenThinker3-1.5B

State-of-the-art SFT-only 1.5B reasoning model. 🚀

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the OpenThoughts3-1.2M dataset.

See our paper and blog post for more details.

Evaluation Results

The numbers reported in the table below are evaluated with our open-source tool Evalchemy. In the table below, we bold values in each column that are within 2 standard errors of the best.

Model	AIME24	AIME25	AMC23	MATH500	HMMT O2/25	LCB 06/24-01/25	CodeElo	CodeForces	GPQA-D	JEEBench
OpenThinker3-1.5B	52.0	41.7	87.0	86.4	27.3	39.4	12.9	15.5	29.5	51.9
DeepSeek-R1-Distill-Qwen-1.5B	32.3	23.7	71.8	80.8	15.3	27.2	8.8	8.5	31.1	32.5
Nemotron-Research-Reasoning-Qwen-1.5B	47.7	32.0	87.5	86.0	21.7	31.4	54.7	40.3	41.8	52.6
Qwen3-1.7B	52.0	35.3	83.8	87.2	23.3	27.7	20.7	20.0	49.3	60.7
Qwen2.5-1.5B-Instruct	3.0	0.7	30.8	50.2	0.0	5.5	0.8	2.2	24.7	16.4

Data

This model was trained on the OpenThoughts3-1.2M dataset.

The key to the strong model performance is our comprehensive data pipeline and over 1,000+ ablation experiments. This led to the creation of OpenThoughts3-1.2M, which consists of 850,000 math questions, 250,000 code questions, and 100,000 science questions. Reasoning traces are generated with QwQ-32B.

See the OpenThoughts3-1.2M dataset page or our paper for additional information.

Intended uses & limitations

Apache 2.0 License

Training procedure

We used 64 A100 gpus to train the model for 7 days.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00016
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 64
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7.0

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.1.0
Tokenizers 0.20.3

More info can be found in our repository: https://github.com/open-thoughts/open-thoughts.

Citation

@misc{guha2025openthoughtsdatarecipesreasoning,
  title={OpenThoughts: Data Recipes for Reasoning Models}, 
  author={Etash Guha and Ryan Marten and Sedrick Keh and Negin Raoof and Georgios Smyrnis and Hritik Bansal and Marianna Nezhurina and Jean Mercat and Trung Vu and Zayne Sprague and Ashima Suvarna and Benjamin Feuer and Liangyu Chen and Zaid Khan and Eric Frankel and Sachin Grover and Caroline Choi and Niklas Muennighoff and Shiye Su and Wanjia Zhao and John Yang and Shreyas Pimpalgaonkar and Kartik Sharma and Charlie Cheng-Jie Ji and Yichuan Deng and Sarah Pratt and Vivek Ramanujan and Jon Saad-Falcon and Jeffrey Li and Achal Dave and Alon Albalak and Kushal Arora and Blake Wulfe and Chinmay Hegde and Greg Durrett and Sewoong Oh and Mohit Bansal and Saadia Gabriel and Aditya Grover and Kai-Wei Chang and Vaishaal Shankar and Aaron Gokaslan and Mike A. Merrill and Tatsunori Hashimoto and Yejin Choi and Jenia Jitsev and Reinhard Heckel and Maheswaran Sathiamoorthy and Alexandros G. Dimakis and Ludwig Schmidt},
  year={2025},
  eprint={2506.04178},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2506.04178}, 
}