Instructions to use mailabs/MiaBee-VL-4B-TR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use mailabs/MiaBee-VL-4B-TR 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 mailabs/MiaBee-VL-4B-TR:Q4_K_M # Run inference directly in the terminal: llama cli -hf mailabs/MiaBee-VL-4B-TR:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mailabs/MiaBee-VL-4B-TR:Q4_K_M # Run inference directly in the terminal: llama cli -hf mailabs/MiaBee-VL-4B-TR: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 mailabs/MiaBee-VL-4B-TR:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf mailabs/MiaBee-VL-4B-TR:Q4_K_M
Use Docker
docker model run hf.co/mailabs/MiaBee-VL-4B-TR:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use mailabs/MiaBee-VL-4B-TR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mailabs/MiaBee-VL-4B-TR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mailabs/MiaBee-VL-4B-TR", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/mailabs/MiaBee-VL-4B-TR:Q4_K_M
- Ollama
How to use mailabs/MiaBee-VL-4B-TR with Ollama:
ollama run hf.co/mailabs/MiaBee-VL-4B-TR:Q4_K_M
- Unsloth Desktop
- Pi
How to use mailabs/MiaBee-VL-4B-TR with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf mailabs/MiaBee-VL-4B-TR: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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "mailabs/MiaBee-VL-4B-TR:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use mailabs/MiaBee-VL-4B-TR with Docker Model Runner:
docker model run hf.co/mailabs/MiaBee-VL-4B-TR:Q4_K_M
- Lemonade
How to use mailabs/MiaBee-VL-4B-TR with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mailabs/MiaBee-VL-4B-TR:Q4_K_M
Run and chat with the model
lemonade run user.MiaBee-VL-4B-TR-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use mailabs/MiaBee-VL-4B-TR with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf mailabs/MiaBee-VL-4B-TR: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://127.0.0.1:9931/v1 hermes config set model.default mailabs/MiaBee-VL-4B-TR:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use mailabs/MiaBee-VL-4B-TR with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf mailabs/MiaBee-VL-4B-TR: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://127.0.0.1:9931/v1 \ --custom-model-id "mailabs/MiaBee-VL-4B-TR: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"
MiaBee-VL-4B-TR (beta)
Turkish-adapted Qwen3-VL-4B-Instruct with vision retained. GGUF Q4_K_M.
Beta. Experimental Turkish adaptation, not a replacement for the base model.
Training
QLoRA r=32, 1 epoch, 405 steps, vision tower frozen.
Data: 3,485 Turkish instruction samples + 3,000 from merve/turkish_instructions.
Evaluation (self-run, not official)
| Test | This model | Base |
|---|---|---|
| TurkishMMLU, 5-shot, 900 q | 55.8% | 54.3% |
| Turkish instruction-following, 20 tasks | 65% | 70% |
| ScreenSpot-v2 Desktop, 334 screenshots | 62.9% | โ |
| Tool calling, 10 tasks | 9/10 | โ |
Differences on the first two rows are within noise. This model does not outperform the base.
Usage
llama-server -m MiaBee-VL-4B-TR-Q4_K_M.gguf --mmproj mmproj-Q8_0.gguf \
-c 4096 -np 1 --jinja -ctk q8_0 -ctv q8_0
~400 MB RAM text, ~900 MB with vision, ~45 tok/s.
Limitations
Hallucinates numbers; can loop on open-ended prompts; does not retry after tool errors; mmproj must be Q8_0 (Q4_0 is broken).
License
Apache 2.0. Derivative of Qwen3-VL-4B-Instruct.
- Downloads last month
- 51
4-bit
Model tree for mailabs/MiaBee-VL-4B-TR
Base model
Qwen/Qwen3-VL-4B-Instruct