---
license: other
license_name: qwen
language:
- th
- en
base_model: openthaigpt/openthaigpt-1.6-72b-instruct
pipeline_tag: text-generation
library_name: gguf
tags:
- thai
- openthai
- gguf
- llama.cpp
---

<div align="center">
<img src="https://huggingface.co/spaces/openthaigpt/README/resolve/main/openthai-logo-white.png" width="160" alt="OpenThai">

# OpenThaiGPT 1.6 72B — GGUF

**Official** GGUF quantizations of [openthaigpt/openthaigpt-1.6-72b-instruct](https://huggingface.co/openthaigpt/openthaigpt-1.6-72b-instruct)

[Website](https://openthai.aieat.or.th) · [Leaderboard](https://huggingface.co/spaces/openthaigpt/thai-llm-leaderboard) · [Discord](https://discord.gg/7KDdKkBGUs) · [Paper](https://arxiv.org/abs/2504.01789)
</div>

The general-purpose workhorse of the OpenThai family — 98.2% Thai language accuracy,
strongest of the family on Thai coding (LiveCodeBench-TH 32.43). These are the official
quantizations, built from the source weights by the OpenThai team.

For step-by-step reasoning use
[R1 32B](https://huggingface.co/openthaigpt/openthaigpt-r1-32b-instruct-GGUF) — smaller
and better at it. For a laptop, use
[1.5 7B](https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct-GGUF).

## Quants

| File | Quant | Size | Notes |
|---|---|---|---|
| `openthaigpt-1.6-72b-instruct.Q4_K_M.gguf` | Q4_K_M | ~44 GB | **Recommended.** 2× 24 GB GPUs or a 64 GB Mac. |
| `openthaigpt-1.6-72b-instruct.Q5_K_M.gguf` | Q5_K_M | ~51 GB | Higher quality. |
| `openthaigpt-1.6-72b-instruct.Q8_0.gguf` | Q8_0 | ~77 GB | Near-lossless. |

## Usage

**Ollama**

```bash
ollama run hf.co/openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
```

**llama.cpp**

```bash
llama-cli -m openthaigpt-1.6-72b-instruct.Q4_K_M.gguf \
  -p "เขียนฟังก์ชัน Python แปลงเลขไทยเป็นเลขอารบิก พร้อมอธิบายโค้ด" -n 2048 --temp 0.7
```

Uses the **ChatML** template (`<|im_start|>` / `<|im_end|>`), embedded in the GGUF.
Recommended sampling: `temperature=0.7`, `top_p=0.9`.

## Citation

```bibtex
@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}
}
```

---

*OpenThai (formerly OpenThaiGPT) — free, open-weight Thai large language models from AIEAT
and iApp Technology. With thanks to the community members who published unofficial GGUF
conversions before these existed.*