Instructions to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openthaigpt/openthaigpt-1.6-72b-instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openthaigpt/openthaigpt-1.6-72b-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Ollama
How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with Ollama:
```
ollama run hf.co/openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for openthaigpt/openthaigpt-1.6-72b-instruct-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for openthaigpt/openthaigpt-1.6-72b-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for openthaigpt/openthaigpt-1.6-72b-instruct-GGUF to start chatting

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M
```

Lemonade

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.openthaigpt-1.6-72b-instruct-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use openthaigpt/openthaigpt-1.6-72b-instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default openthaigpt/openthaigpt-1.6-72b-instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenThaiGPT 1.6 72B — GGUF

Official GGUF quantizations of openthaigpt/openthaigpt-1.6-72b-instruct

Website · Leaderboard · Discord · Paper

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 — smaller and better at it. For a laptop, use 1.5 7B.

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

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

llama.cpp

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

@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.

Downloads last month: 236

GGUF

Model size

73B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for openthaigpt/openthaigpt-1.6-72b-instruct-GGUF

Base model

openthaigpt/openthaigpt-1.6-72b-instruct

Quantized

(4)

this model

Paper for openthaigpt/openthaigpt-1.6-72b-instruct-GGUF

OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models

Paper • 2504.01789 • Published Apr 2, 2025 • 2