Instructions to use bombman/ChindaMT-4B-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 bombman/ChindaMT-4B-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 bombman/ChindaMT-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bombman/ChindaMT-4B-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 bombman/ChindaMT-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bombman/ChindaMT-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf bombman/ChindaMT-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf bombman/ChindaMT-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bombman/ChindaMT-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use bombman/ChindaMT-4B-GGUF with Ollama:
```
ollama run hf.co/bombman/ChindaMT-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bombman/ChindaMT-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bombman/ChindaMT-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bombman/ChindaMT-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bombman/ChindaMT-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/bombman/ChindaMT-4B-GGUF:Q4_K_M
```

Lemonade

How to use bombman/ChindaMT-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bombman/ChindaMT-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ChindaMT-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bombman/ChindaMT-4B-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 bombman/ChindaMT-4B-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 bombman/ChindaMT-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bombman/ChindaMT-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bombman/ChindaMT-4B-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 "bombman/ChindaMT-4B-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"

🇹🇭 ChindaMT-4B GGUF

GGUF conversion of iapp/ChindaMT-4B for:

llama.cpp
Ollama
LM Studio
Open WebUI
Local AI workflows

ChindaMT-4B is a Thai-focused LLM developed by iApp Technology, optimized for Thai language understanding, reasoning, and local AI deployment.

📦 Available Quantizations

Quant	Quality	Speed	RAM Usage	Recommended For
F16	Best	Slow	High	Benchmark / Fine-tune
Q8_0	Excellent	Medium	Medium-High	High-end GPU
Q4_K_M	Very Good	Fast	Medium	Daily usage ⭐
Q4_K_S	Good	Very Fast	Low	Laptop / Edge device

⭐ Recommended Version

Q4_K_M

Best balance between:

Quality
Speed
Memory usage

📥 Download

Available files:

ChindaMT-4B-F16.gguf
ChindaMT-4B-Q8_0.gguf
ChindaMT-4B-Q4_K_M.gguf
ChindaMT-4B-Q4_K_S.gguf

🚀 Usage

llama.cpp

CLI

./llama-cli \
  -m ChindaMT-4B-Q4_K_M.gguf \
  -p "สวัสดี ช่วยอธิบาย quantum computing แบบง่าย"

Server

./llama-server \
  -m ChindaMT-4B-Q4_K_M.gguf \
  --host 0.0.0.0 \
  --port 8080

🦙 Ollama

Create Modelfile

FROM ./ChindaMT-4B-Q4_K_M.gguf

Build

ollama create chindamt -f Modelfile

Run

ollama run chindamt

💻 LM Studio

Open LM Studio
Go to Models
Import .gguf
Select quantization
Start chatting

Recommended:

Q4_K_M for most users
Q8_0 if you have more VRAM

⚡ Hardware Recommendation

Quant	Recommended RAM
Q4_K_S	6GB+
Q4_K_M	8GB+
Q8_0	12GB+
F16	16GB+

GPU acceleration supported:

CUDA
Vulkan
Metal
ROCm

🧠 Quantization Notes

F16

Highest quality and accuracy.

Best for:

Benchmarking
Fine-tuning
Powerful GPUs

Q8_0

Very close to F16 quality with reduced memory usage.

Best for:

Workstations
Desktop GPUs

Q4_K_M ⭐

Best overall balance.

Most recommended quantization for:

Daily usage
AI agents
Local assistants

Q4_K_S

Smallest and fastest version.

Best for:

Laptops
Raspberry Pi
Low RAM systems

🔥 Suggested Use Cases

Thai AI Assistant
Coding Assistant
Local RAG
Obsidian AI
Open WebUI
n8n AI Workflow
Autonomous Agent
Raspberry Pi AI

📊 Base Model

Base: Qwen3-4B
Optimized for Thai language
Developed by iApp Technology
License: Apache 2.0

Official links:

📜 License

Apache 2.0

Commercial use allowed.

🙌 Credits

iApp Technology
Qwen Team
llama.cpp
GGUF community

❤️ Thai Open Source AI

Built for Thai developers 🇹🇭

Downloads last month: 190

GGUF

Model size

5B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bombman/ChindaMT-4B-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

iapp/ChindaMT-4B

Quantized

(4)

this model