Skip to main content

🏠 Welcome to OpenThaiGPT 1.6 and OpenThaiGPT R1

OpenThaiGPT

🇹🇭 OpenThaiGPT 1.6 72b, the latest large language model improved from version 1.5, and 🧠 OpenThaiGPT R1 32b, a model focused on analytical thinking and reasoning, are now available. These models were developed for general-purpose use and offer strong reasoning capabilities, particularly in the Thai language.

Try It Out​

Try it on ChindaXchindax.iapp.co.th

Download the Models​

OpenThaiGPT 1.6 72b — Hugging Facehuggingface.co

OpenThaiGPT R1 32b — Hugging Facehuggingface.co

🌟 OpenThaiGPT 1.6 72b​

OpenThaiGPT 1.6 72b is a 72-billion-parameter Thai language model designed for general-purpose tasks with strong analytical thinking capabilities. Building on the foundation of OpenThaiGPT 1.5, this latest release demonstrates improved performance across a wide range of benchmarks, particularly in coding and general language tasks.

Highlights of OpenThaiGPT 1.6 72b​

  • Advanced Thai language model with 72 billion parameters
  • Strong analytical thinking capabilities in both Thai and English
  • Improved performance compared to previous OpenThaiGPT releases
  • Balanced capabilities across mathematics, coding, and general language tasks
  • Deep understanding of the Thai language and cultural context

Key Improvements in OpenThaiGPT 1.6 72b​

Compared to OpenThaiGPT 1.5 72b, version 1.6 demonstrates:

  • Substantially improved coding performance in both Thai (LiveCodeBench-TH: 32.43 vs 12.61) and English (LiveCodeBench: 54.21 vs 46.38)
  • Comparable general language understanding with language accuracy as high as 98.2%
  • Better balanced capabilities between mathematics and coding tasks

🧠 OpenThaiGPT R1 32b​

OpenThaiGPT R1 32b is an advanced 32-billion-parameter Thai language model focused on analytical thinking and reasoning, outperforming larger models such as DeepSeek R1 70b and Typhoon R1 70b despite being less than half their size. The model excels at tasks requiring complex analytical thinking, including mathematics, logic, and coding in the Thai language.

Highlights of OpenThaiGPT R1 32b​

  • State-of-the-art Thai language model that outperforms larger models on mathematics and logical reasoning benchmarks
  • Explicit reasoning capabilities able to show its thought process step by step
  • Significantly smaller size (32b) yet higher performance than 70b models
  • Specialized in analytical thinking in Thai, including complex mathematical and logical problems
  • High coding performance in both Thai and English

Benchmark Results​

OpenThaiGPT 1.6 72b​

BenchmarksOpenThaiGPT 1.6 72bOpenThaiGPT 1.5 7bOpenThaiGPT 1.5 14bOpenThaiGPT 1.5 72bTyphoon2 Qwen2.5 7bTyphoon2 Llama3.1 8bTyphoon2 Llama3.1 70bNECTEC Pathumma LLM Text 1.0.0 7b
AIME24-TH6.67006.673.333.3313.330
AIME2423.336.671023.336.673.33100
MATH500-TH43.224.226.26251.83155.821.8
MATH5008240.447.483.265.449.667.442.8
LiveCodeBench-TH32.4322.5221.6212.619.918.1127.030
LiveCodeBench54.2131.1237.9646.380.985.8737.380
OpenThaiEval78.764.571.2677.1664.7656.6372.5465.27
Language Accuracy98.297.698.499.499.498.699.898.6
AVERAGE52.3435.8839.1151.3437.7832.0647.9128.56

OpenThaiGPT R1 32b​

SkyThoughtOpenThaiGPT R1 32bDeepSeek R1 70bTyphoon R1 70b
AIME24-TH56.6733.3353.33
AIME2463.3653.3353.33
MATH500-TH83.875.481
MATH50089.488.8890.2
LiveCodeBench-TH62.1653.1547.75
LiveCodeBench69.6764.9754.79
OpenThaiEval76.0574.1777.59
AVERAGE71.5863.3165.42

Model Technical Report​

OpenThaiGPT 1.6 and R1 Technical Report — arXivarxiv.org

If OpenThaiGPT has been beneficial for your work, kindly consider citing it as follows:

@misc{yuenyong2025openthaigpt16r1thaicentric,
      title={OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models}, 
      author={Sumeth Yuenyong and Thodsaporn Chay-intr and Kobkrit Viriyayudhakorn},
      year={2025},
      eprint={2504.01789},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2504.01789}, 
}

How to Use​

Online Web Interface​

ChindaX — Online Web Interfacechindax.iapp.co.th

Transformers​

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "openthaigpt/openthaigpt-1.6-72b" #openthaigpt/openthaigpt-r1-32b-instruct

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "กรุงเทพมหานครคืออะไร"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=8192,
    temperature=0.6
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

vLLM​

  1. Install vLLM (vllm-project/vllm)
  2. Run server (choose one)
vllm serve openthaigpt/openthaigpt-1.6-72b --tensor-parallel-size 2
vllm serve openthaigpt/openthaigpt-r1-32b-instruct --tensor-parallel-size 2
  • Note, change --tensor-parallel-size 2 to the amount of available GPU cards.
  1. Run inference (CURL example)
curl -X POST 'http://127.0.0.1:8000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-d '{
  "model": "openthaigpt/openthaigpt-1.6-72b",
  "messages": [
    {
      "role": "user",
      "content": "กรุงเทพมหานครคืออะไร"
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.6,
  "top_p": 0.95,
  "top_k": 40
}'

Or change the model name to "model": "openthaigpt/openthaigpt-r1-32b-instruct" or "model": "openthaigpt/openthaigpt-1.6-72b".

GPU Memory Requirements​

Number of ParametersFP 16 bits8 bits (Quantized)4 bits (Quantized)
32b64 GB32 GB16 GB
72b144 GB72 GB36 GB

License​

  • This model is available for research and commercial use under the terms of the Qwen2.5 license agreement. Please refer to the LICENSE file for more information.

Support​

The OpenThaiGPT Team​

Sponsors​

  • Supported with 8x Nvidia H100 GPUs by Siam AI Corporation Co., Ltd.: siam.ai
  • Funded by a research grant from the Science, Research and Innovation Promotion Fund, through the Program Management Unit for Competitiveness (PMUC), in collaboration with iApp Technology Co., Ltd., with the Artificial Intelligence Entrepreneur Association of Thailand as the project operator

Disclaimer: Provided responses are not guaranteed.