Skip to main content

🌟 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.

Download the model

OpenThaiGPT 1.6 72b — Hugging Facehuggingface.co

openthaigpt/openthaigpt-1.6-72b-instruct

Highlights

  • 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 over 1.5

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

Benchmark results

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

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

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "openthaigpt/openthaigpt-1.6-72b"

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
vllm serve openthaigpt/openthaigpt-1.6-72b --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
}'

GPU memory requirements

Number of ParametersFP 16 bits8 bits (Quantized)4 bits (Quantized)
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

Disclaimer: Provided responses are not guaranteed.