Chinda-qwen3-4b-gguf Open-Source Thai Model - Empowering the Thai AI Ecosystem with Advanced Thinking Abilities

Chinda Qwen3 4b Gguf

Developed by iapp

Chinda LLM 4B is a cutting-edge Thai model launched by iApp Technology, built on the Qwen3-4B architecture, bringing advanced thinking capabilities to the Thai AI ecosystem.

Large Language Model Open Source License:Apache-2.0 #Thai language optimization #Thinking mode #Local deployment

Downloads 115

Release Time : 6/4/2025

Model Overview

A large language model with 4B parameters focusing on Thai language processing, featuring excellent reasoning ability and Thai language accuracy, supporting the switch between thinking mode and non-thinking mode.

Model Features

Advanced thinking model

Supports the thinking mode to show the reasoning process, performing best among Thai models at the 4B parameter level

High accuracy in Thai

The accuracy of Thai output reaches 98.4%, specifically optimized for the Thai language pattern

Latest architecture

Based on the cutting-edge Qwen3-4B model, incorporating the latest progress in language modeling

Free and open source

Follows the Apache 2.0 license, allowing commercial use and unrestricted construction

Model Capabilities

Thai text generation

Multi-round dialogue

Code generation

Mathematical problem solving

Multi-language support

Long context processing

Use Cases

RAG application

Autonomous AI system

Build a retrieval-augmented generation system to ensure data processing within the sovereignty of Thailand

Mobile application

Edge device deployment

A small language model running on mobile devices and laptops

Education

Mathematics tutoring

Solve mathematical problems and show the problem-solving steps

Scored 0.908 in English and 0.612 in Thai in the MATH500 benchmark test

Programming

Code assistant

Generate and explain programming code

Scored 0.665 in English and 0.198 in Thai in the LiveCodeBench benchmark test

🚀 Chinda Opensource Thai LLM 4B (GGUF Q4_K_M)

The latest Thai language model, capable of thinking and answering in Thai, developed by a Thai startup.

image/jpeg

Chinda Opensource Thai LLM 4B is a state - of - the - art Thai language model by iApp Technology. It brings advanced thinking capabilities to the Thai AI ecosystem. Built on the latest Qwen3 - 4B architecture, Chinda showcases our commitment to developing sovereign AI solutions for Thailand.

🚀 Quick Start

Installation

pip install transformers torch

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "iapp/chinda-qwen3-4b"

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# Prepare the model input
prompt = "‡∏≠‡∏ò‡∏¥‡∏ö‡∏≤‡∏¢‡πÄ‡∏Å‡∏µ‡πà‡∏¢‡∏ß‡∏Å‡∏±‡∏ö‡∏õ‡∏±‡∏ç‡∏ç‡∏≤‡∏õ‡∏£‡∏∞‡∏î‡∏¥‡∏©‡∏ê‡πå‡πÉ‡∏´‡πâ‡∏ü‡∏±‡∏á‡∏´‡∏ô‡πà‡∏≠‡∏¢"
messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True  # Enable thinking mode for better reasoning
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
    do_sample=True
)

output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

# Parse thinking content (if enabled)
try:
    # Find </think> token (151668)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("üß† Thinking:", thinking_content)
print("üí¨ Response:", content)

Switching Between Thinking and Non - Thinking Mode

Enable Thinking Mode (Default)

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True  # Enable detailed reasoning
)

Disable Thinking Mode (For Efficiency)

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False  # Fast response mode
)

API Deployment

Using vLLM

pip install vllm>=0.8.5
vllm serve iapp/chinda-qwen3-4b --enable-reasoning --reasoning-parser deepseek_r1

Using SGLang

pip install sglang>=0.4.6.post1
python -m sglang.launch_server --model-path iapp/chinda-qwen3-4b --reasoning-parser qwen3

Using Ollama (Easy Local Setup)

Installation:

# Install Ollama (if not already installed)
curl -fsSL https://ollama.com/install.sh | sh

# Pull Chinda LLM 4B model
ollama pull iapp/chinda-qwen3-4b

Basic Usage:

# Start chatting with Chinda LLM
ollama run iapp/chinda-qwen3-4b

# Example conversation
ollama run iapp/chinda-qwen3-4b "‡∏≠‡∏ò‡∏¥‡∏ö‡∏≤‡∏¢‡πÄ‡∏Å‡∏µ‡πà‡∏¢‡∏ß‡∏Å‡∏±‡∏ö‡∏õ‡∏±‡∏ç‡∏ç‡∏≤‡∏õ‡∏£‡∏∞‡∏î‡∏¥‡∏©‡∏ê‡πå‡πÉ‡∏´‡πâ‡∏ü‡∏±‡∏á‡∏´‡∏ô‡πà‡∏≠‡∏¢"

API Server:

# Start Ollama API server
ollama serve

# Use with curl
curl http://localhost:11434/api/generate -d '{
  "model": "iapp/chinda-qwen3-4b",
  "prompt": "‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ‡∏Ñ‡∏£‡∏±‡∏ö",
  "stream": false
}'

Model Specifications:

Size: 2.5GB (quantized)
Context Window: 40K tokens
Architecture: Optimized for local deployment
Performance: Fast inference on consumer hardware

✨ Features

0. Free and Opensource for Everyone

Chinda LLM 4B is completely free and open - source, enabling developers, researchers, and businesses to build Thai AI applications without restrictions.

1. Advanced Thinking Model

Highest score among Thai LLMs in 4B category
Seamless switching between thinking and non - thinking modes
Superior reasoning capabilities for complex problems
Can be turned off for efficient general - purpose dialogue

2. Exceptional Thai Language Accuracy

98.4% accuracy in outputting Thai language
Prevents unwanted Chinese and foreign language outputs
Specifically fine - tuned for Thai linguistic patterns

3. Latest Architecture

Based on the cutting - edge Qwen3 - 4B model
Incorporates the latest advancements in language modeling
Optimized for both performance and efficiency

4. Apache 2.0 License

Commercial use permitted
Modification and distribution allowed
No restrictions on private use

📦 Installation Guide

The installation steps are as follows:

pip install transformers torch

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "iapp/chinda-qwen3-4b"

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# Prepare the model input
prompt = "‡∏≠‡∏ò‡∏¥‡∏ö‡∏≤‡∏¢‡πÄ‡∏Å‡∏µ‡πà‡∏¢‡∏ß‡∏Å‡∏±‡∏ö‡∏õ‡∏±‡∏ç‡∏ç‡∏≤‡∏õ‡∏£‡∏∞‡∏î‡∏¥‡∏©‡∏ê‡πå‡πÉ‡∏´‡πâ‡∏ü‡∏±‡∏á‡∏´‡∏ô‡πà‡∏≠‡∏¢"
messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True  # Enable thinking mode for better reasoning
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate response
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
    do_sample=True
)

output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

# Parse thinking content (if enabled)
try:
    # Find </think> token (151668)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("üß† Thinking:", thinking_content)
print("üí¨ Response:", content)

Advanced Usage

Switching Between Thinking and Non - Thinking Mode

# Enable Thinking Mode (Default)
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True  # Enable detailed reasoning
)

# Disable Thinking Mode (For Efficiency)
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False  # Fast response mode
)

API Deployment

# Using vLLM
pip install vllm>=0.8.5
vllm serve iapp/chinda-qwen3-4b --enable-reasoning --reasoning-parser deepseek_r1

# Using SGLang
pip install sglang>=0.4.6.post1
python -m sglang.launch_server --model-path iapp/chinda-qwen3-4b --reasoning-parser qwen3

# Using Ollama (Easy Local Setup)
# Installation
curl -fsSL https://ollama.com/install.sh | sh
ollama pull iapp/chinda-qwen3-4b

# Basic Usage
ollama run iapp/chinda-qwen3-4b
ollama run iapp/chinda-qwen3-4b "‡∏≠‡∏ò‡∏¥‡∏ö‡∏≤‡∏¢‡πÄ‡∏Å‡∏µ‡πà‡∏¢‡∏ß‡∏Å‡∏±‡∏ö‡∏õ‡∏±‡∏ç‡∏ç‡∏≤‡∏õ‡∏£‡∏∞‡∏î‡∏¥‡∏©‡∏ê‡πå‡πÉ‡∏´‡πâ‡∏ü‡∏±‡∏á‡∏´‡∏ô‡πà‡∏≠‡∏¢"

# API Server
ollama serve
curl http://localhost:11434/api/generate -d '{
  "model": "iapp/chinda-qwen3-4b",
  "prompt": "‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ‡∏Ñ‡∏£‡∏±‡∏ö",
  "stream": false
}'

📚 Documentation

Benchmark Results

Chinda LLM 4B demonstrates superior performance compared to other Thai language models in its category:

Benchmark	Language	Chinda LLM 4B	Alternative*
AIME24	English	0.533	0.100
	Thai	0.100	0.000
LiveCodeBench	English	0.665	0.209
	Thai	0.198	0.144
MATH500	English	0.908	0.702
	Thai	0.612	0.566
IFEVAL	English	0.849	0.848
	Thai	0.683	0.740
Language Accuracy	Thai	0.984	0.992
OpenThaiEval	Thai	0.651	0.544
AVERAGE		0.569	0.414

Alternative: scb10x_typhoon2.1 - gemma3 - 4b
Tested by Skythought and Evalscope Benchmark Libraries by iApp Technology team. Results show Chinda LLM 4B achieving 37% better overall performance than the nearest alternative.

Suitable For

RAG Applications (Sovereign AI): Perfect for building Retrieval - Augmented Generation systems that keep data processing within Thai sovereignty.
Mobile and Laptop Applications: Reliable Small Language Model optimized for edge computing and personal devices.
Math Calculation: Excellent performance in mathematical reasoning and problem - solving.
Code Assistant: Strong capabilities in code generation and programming assistance.
Resource Efficiency: Very fast inference with minimal GPU memory consumption, ideal for production deployments.

Not Suitable For

As a 4B parameter model, it may hallucinate when asked for specific facts without provided context. Always use with RAG or provide relevant context for factual queries.

Advanced Configuration

Processing Long Texts

Chinda LLM 4B natively supports up to 32,768 tokens. For longer contexts, enable YaRN scaling:

{
    "rope_scaling": {
        "rope_type": "yarn",
        "factor": 4.0,
        "original_max_position_embeddings": 32768
    }
}

Recommended Parameters

For Thinking Mode:

Temperature: 0.6
Top - P: 0.95
Top - K: 20
Min - P: 0

For Non - Thinking Mode:

Temperature: 0.7
Top - P: 0.8
Top - K: 20
Min - P: 0

Context Length & Template Format

Context Length Support

Native Context Length: 32,768 tokens
Extended Context Length: Up to 131,072 tokens (with YaRN scaling)
Input + Output: Total conversation length supported
Recommended Usage: Keep conversations under 32K tokens for optimal performance

Chat Template Format

Chinda LLM 4B uses a standardized chat template format for consistent interactions:

# Basic template structure
messages = [
    {"role": "system", "content": "You are a helpful Thai AI assistant."},
    {"role": "user", "content": "‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ‡∏Ñ‡∏£‡∏±‡∏ö"},
    {"role": "assistant", "content": "‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ‡∏Ñ‡πà‡∏∞! ‡∏°‡∏µ‡∏≠‡∏∞‡πÑ‡∏£‡πÉ‡∏´‡πâ‡∏ä‡πà‡∏ß‡∏¢‡πÄ‡∏´‡∏•‡∏∑‡∏≠‡∏ö‡πâ‡∏≤‡∏á‡∏Ñ‡∏∞"},
    {"role": "user", "content": "‡∏ä‡πà‡∏ß‡∏¢‡∏≠‡∏ò‡∏¥‡∏ö‡∏≤‡∏¢‡πÄ‡∏£‡∏∑‡πà‡∏≠‡∏á AI ‡πÉ‡∏´‡πâ‡∏ü‡∏±‡∏á‡∏´‡∏ô‡πà‡∏≠‡∏¢"}
]

# Apply template with thinking mode
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True
)

Template Structure

The template follows the standard conversational format:

<|im_start|>system
You are a helpful Thai AI assistant.<|im_end|>
<|im_start|>user
‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ‡∏Ñ‡∏£‡∏±‡∏ö<|im_end|>
<|im_start|>assistant
‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ‡∏Ñ‡πà‡∏∞! ‡∏°‡∏µ‡∏≠‡∏∞‡πÑ‡∏£‡πÉ‡∏´‡πâ‡∏ä‡πà‡∏ß‡∏¢‡πÄ‡∏´‡∏•‡∏∑‡∏≠‡∏ö‡πâ‡∏≤‡∏á‡∏Ñ‡∏∞<|im_end|>
<|im_start|>user
‡∏ä‡πà‡∏ß‡∏¢‡∏≠‡∏ò‡∏¥‡∏ö‡∏≤‡∏¢‡πÄ‡∏£‡∏∑‡πà‡∏≠‡∏á AI ‡πÉ‡∏´‡πâ‡∏ü‡∏±‡∏á‡∏´‡∏ô‡πà‡∏≠‡∏¢<|im_end|>
<|im_start|>assistant

Advanced Template Usage

# Multi - turn conversation with thinking control
def create_conversation(messages, enable_thinking=True):
    # Add system message if not present
    if not messages or messages[0]["role"] != "system":
        system_msg = {
            "role": "system", 
            "content": "‡∏Ñ‡∏∏‡∏ì‡πÄ‡∏õ‡πá‡∏ô AI ‡∏ú‡∏π‡πâ‡∏ä‡πà‡∏ß‡∏¢‡∏ó‡∏µ‡πà‡∏â‡∏•‡∏≤‡∏î‡πÅ‡∏•‡∏∞‡πÄ‡∏õ‡πá‡∏ô‡∏õ‡∏£‡∏∞‡πÇ‡∏¢‡∏ä‡∏ô‡πå ‡∏û‡∏π‡∏î‡∏†‡∏≤‡∏©‡∏≤‡πÑ‡∏ó‡∏¢‡πÑ‡∏î‡πâ‡∏≠‡∏¢‡πà‡∏≤‡∏á‡πÄ‡∏õ‡πá‡∏ô‡∏ò‡∏£‡∏£‡∏°‡∏ä‡∏≤‡∏ï‡∏¥"
        }
        messages = [system_msg] + messages
    
    # Apply chat template
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True,
        enable_thinking=enable_thinking
    )
    
    return text

# Example usage
conversation = [
    {"role": "user", "content": "‡∏Ñ‡∏≥‡∏ô‡∏ß‡∏ì 15 √ó 23 = ?"},
]

prompt = create_conversation(conversation, enable_thinking=True)

Dynamic Mode Switching

You can control thinking mode within conversations using special commands:

# Enable thinking for complex problems
messages = [
    {"role": "user", "content": "/think ‡πÅ‡∏Å‡πâ‡∏™‡∏°‡∏Å‡∏≤‡∏£: x¬≤ + 5x - 14 = 0"}
]

# Disable thinking for quick responses  
messages = [
    {"role": "user", "content": "/no_think ‡∏™‡∏ß‡∏±‡∏™‡∏î‡∏µ"}
]

Context Management Best Practices

Monitor Token Count: Keep track of total tokens (input + output).
Truncate Old Messages: Remove oldest messages when approaching limits.
Use YaRN for Long Contexts: Enable rope scaling for documents > 32K tokens.
Batch Processing: For very long texts, consider chunking and processing in batches.

def manage_context(messages, max_tokens=30000):
    """Simple context management function"""
    total_tokens = sum(len(tokenizer.encode(msg["content"])) for msg in messages)
    
    while total_tokens > max_tokens and len(messages) > 2:
        # Keep system message and remove oldest user/assistant pair
        if messages[1]["role"] == "user":
            messages.pop(1)  # Remove user message
            if len(messages) > 1 and messages[1]["role"] == "assistant":
                messages.pop(1)  # Remove corresponding assistant message
        
        total_tokens = sum(len(tokenizer.encode(msg["content"])) for msg in messages)
    
    return messages

Enterprise Support

For enterprise deployments, custom training, or commercial support, contact us at:

Email: sale@iapp.co.th
Website: iapp.co.th

Frequently Asked Questions

Why is it named "Chinda"?

The name "Chinda" (‡∏à‡∏¥‡∏ô‡∏î‡∏≤) comes from "‡∏à‡∏¥‡∏ô‡∏î‡∏≤‡∏°‡∏ì‡∏µ" (Chindamani), which is considered the first book of Thailand written by Phra Horathibodi (Sri Dharmasokaraja) in the Sukhothai period. Just as ‡∏à‡∏¥‡∏ô‡∏î‡∏≤‡∏°‡∏ì‡∏µ was a foundational text for Thai literature and learning, Chinda LLM represents our foundation for Thai sovereign AI - a model that truly understands and thinks in Thai, preserving and advancing Thai language capabilities in the digital age.

Can I use Chinda LLM 4B for commercial purposes?

Yes! Chinda LLM 4B is released under the Apache 2.0 License, which allows:

Commercial use: Use in commercial products and services.
Research use: Academic and research applications.
Modification: Adapt and modify the model.
Distribution: Share and redistribute the model.
Private use: Use for internal company projects.

No restrictions on commercial applications - build and deploy freely!

What's the difference between thinking and non - thinking mode?

Thinking Mode (enable_thinking=True):

Model shows its reasoning process in <think>...</think> blocks.
Better for complex problems, math, coding, logical reasoning.
Slower but more accurate responses.
Recommended for tasks requiring deep analysis.

Non - Thinking Mode (enable_thinking=False):

Direct answers without showing reasoning.
Faster responses for general conversations.
Better for simple queries and chat applications.
More efficient resource usage.

You can switch between modes or let users control it dynamically using /think and /no_think commands.

How does Chinda LLM 4B compare to other Thai language models?

Chinda LLM 4B achieves 37% better overall performance compared to the nearest alternative:

Overall Average: 0.569 vs 0.414 (alternative).
Math (MATH500): 0.908 vs 0.702 (English), 0.612 vs 0.566 (Thai).
Code (LiveCodeBench): 0.665 vs 0.209 (English), 0.198 vs 0.144 (Thai).
Thai Language Accuracy: 98.4% (prevents Chinese/foreign text output).
OpenThaiEval: 0.651 vs 0.544.

It's currently the highest - scoring Thai LLM in the 4B parameter category.

What are the system requirements to run Chinda LLM 4B?

Minimum Requirements:

GPU: 8GB VRAM (RTX 3070/4060 Ti or better).
RAM: 16GB system memory.
Storage: 8GB free space for model download.
Python: 3.8+ with PyTorch.

Recommended for Production:

GPU: 16GB+ VRAM (RTX 4080/A4000 or better).
RAM: 32GB+ system memory.
Storage: SSD for faster loading.

CPU - Only Mode: Possible but significantly slower (not recommended for production).

Can I fine - tune Chinda LLM 4B for my specific use case?

Yes! As an open - source model under Apache 2.0 license, you can:

Fine - tune on your domain - specific data.
Customize for specific tasks or industries.
Modify the architecture if needed.
Create derivatives for specialized applications.

Popular fine - tuning frameworks that work with Chinda:

Unsloth: Fast and memory - efficient.
LoRA/QLoRA: Parameter - efficient fine - tuning.
Hugging Face Transformers: Full fine - tuning.
Axolotl: Advanced training configurations.

Need help with fine - tuning? Contact our team at sale@iapp.co.th

What languages does Chinda LLM 4B support?

Primary Languages:

Thai: Native - level understanding and generation (98.4% accuracy).
English: Strong performance across all benchmarks.

Additional Languages:

100+ languages supported (inherited from Qwen3 - 4B base).
Focus optimized for Thai - English bilingual tasks.
Code generation in multiple programming languages.

Special Features:

Code - switching between Thai and English.
Translation between Thai and other languages.
Multilingual reasoning capabilities.

Is the training data publicly available?

The model weights are open - source, but the specific training datasets are not publicly released. However:

Base Model: Built on Qwen3 - 4B (Alibaba's open foundation).
Thai Optimization: Custom dataset curation for Thai language tasks.
Quality Focus: Carefully selected high - quality Thai content.
Privacy Compliant: No personal or sensitive data included.

For research collaborations or dataset inquiries, contact our research team.

How do I get support or report issues?

For Technical Issues:

GitHub Issues: Report bugs and technical problems.
Hugging Face: Model - specific questions and discussions.
Documentation: Check our comprehensive guides.

For Commercial Support:

Email: sale@iapp.co.th
Enterprise Support: Custom training, deployment assistance.
Consulting: Integration and optimization services.

Community Support:

Thai AI Community: Join discussions about Thai AI development.
Developer Forums: Connect with other Chinda users.

How large is the model download and what format is it in?

Model Specifications:

Parameters: 4.02 billion (4B).
Download Size: ~8GB (compressed).
Format: Safetensors (recommended) and PyTorch.
Precision: BF16 (Brain Float 16).

Download Options:

Hugging Face Hub: huggingface.co/iapp/chinda-qwen3-4b.
Git LFS: For version control integration.
Direct Download: Individual model files.
Quantized Versions: Available for reduced memory usage (GGUF, AWQ).

Quantization Options:

4 - bit (GGUF): ~2.5GB, runs on 4GB VRAM.
8 - bit: ~4GB, balanced performance/memory.
16 - bit (Original): ~8GB, full performance.

📄 License

This project is licensed under the Apache 2.0 License.

🔧 Technical Details

Model Information

Property	Details
Model Type	Chinda Opensource Thai LLM 4B (GGUF Q4_K_M)
Base Model	iapp/chinda-qwen3-4b
Pipeline Tag	text-generation
Tags	thai

Citation

If you use Chinda LLM 4B in your research or projects, please cite:

@misc{chinda-llm-4b,
  title={Chinda LLM 4B: Thai Sovereign AI Language Model},
  author={iApp Technology},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/iapp/chinda-qwen3-4b}
}

Built with passion by iApp Technology - Empowering Thai Businesses with Sovereign AI Excellence

image/jpeg

Powered by iApp Technology

Disclaimer: Provided responses are not guaranteed.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご