Sign up

bombman/ChindaMT-4B-GGUF

🤗 Hugging Face sourceapache-2.021 GBGGUF✓ HF checksums availableupdated today
No torrent yet →

🇹🇭 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

  1. Open LM Studio
  2. Go to Models
  3. Import .gguf
  4. Select quantization
  5. 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 🇹🇭