Instructions to use openbmb/MiniCPM5-1B-GGUF 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 openbmb/MiniCPM5-1B-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 openbmb/MiniCPM5-1B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf openbmb/MiniCPM5-1B-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 openbmb/MiniCPM5-1B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf openbmb/MiniCPM5-1B-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 openbmb/MiniCPM5-1B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf openbmb/MiniCPM5-1B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/openbmb/MiniCPM5-1B-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use openbmb/MiniCPM5-1B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/MiniCPM5-1B-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": "openbmb/MiniCPM5-1B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/openbmb/MiniCPM5-1B-GGUF:Q4_K_M
- Ollama
How to use openbmb/MiniCPM5-1B-GGUF with Ollama:
ollama run hf.co/openbmb/MiniCPM5-1B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use openbmb/MiniCPM5-1B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf openbmb/MiniCPM5-1B-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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "openbmb/MiniCPM5-1B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use openbmb/MiniCPM5-1B-GGUF with Docker Model Runner:
docker model run hf.co/openbmb/MiniCPM5-1B-GGUF:Q4_K_M
- Lemonade
How to use openbmb/MiniCPM5-1B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull openbmb/MiniCPM5-1B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.MiniCPM5-1B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use openbmb/MiniCPM5-1B-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 openbmb/MiniCPM5-1B-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://127.0.0.1:9931/v1 hermes config set model.default openbmb/MiniCPM5-1B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use openbmb/MiniCPM5-1B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf openbmb/MiniCPM5-1B-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://127.0.0.1:9931/v1 \ --custom-model-id "openbmb/MiniCPM5-1B-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"
lmstudio 无法正常对话
- lmstudio 全部使用默认加载后在 chat 中无法正常对话,google ai 说是 lmstudio 未正确解析:chat template。
- lmstudio 设置面板 developer 已经开启了 “在预设中启用模型加载配置支持”。
2026-05-27 06:14:36 [DEBUG]
0.00.976.932 I init: chat template, example_format: 'You are a helpful assistantHelloHi thereHow are you?'
2026-05-27 06:14:36 [DEBUG]
0.00.977.490 I srv init: init: chat template, thinking = 0
2026-05-27 06:14:36 [DEBUG]
0.00.977.612 I srv update_slots: all slots are idle
- ./llama-server -m MiniCPM5-1B-F16.gguf --port 8080 -ngl 99 -c 8192 --jinja --flash-attn on --kv-offload --numa distribute 加载正常对话也正常
0.00.925.699 I init: chat template, example_format: '<s><|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
<think>
'
0.00.927.570 I srv init: init: chat template, thinking = 1
Thanks for the report — your diagnosis looks correct. LM Studio isn’t applying the embedded Jinja chat template from the GGUF, so the prompt gets flattened (hence thinking = 0 and the broken example_format).
MiniCPM5 support was recently merged in llama.cpp and works with Jinja enabled. LM Studio bundles its own llama.cpp backend, so you’ll need to wait for them to ship a newer version. For now, use llama-server
Thanks you, now it's work.
LM Studio 0.4.15 (Build 1) release
- llama.cpp release b9334 (commit 5190c2e)
Can you add this message about runing only in LM Studio 0.4.15 (build 1)?
upd. It not working on LM Studio 0.4.15 (build 1)? Same effect.



