openbmb/minicpm/minicpm5-deploy-llama-cpp
Claude Code and agent skill by openbmb/minicpm
- community
Checking that the SKILL.md file is still in the repository.
Run MiniCPM5-1B or MiniCPM5-2B with llama.cpp using the released GGUF artifacts (F16 / Q8_0 / Q4_K_M). Use when the user wants CPU-only / consumer-GPU / cross-platform native deployment, asks for "llama.cpp", "llama-cli", "llama-server", "GGUF", or has no Python available.
Install
npx vskill@latest install openbmb/minicpm/minicpm5-deploy-llama-cppSKILL.md
The same SKILL.md was published earlier as openbmb/minicpm/minicpm5-deploy-llama-cpp.
Deploy MiniCPM5-1B and MiniCPM5-2B with llama.cpp
CPU / edge / consumer-GPU deployment via the released GGUF artifacts. The artifacts work directly with vanilla llama.cpp and every downstream runtime (Ollama / LM Studio / llama-cpp-python).
Required input
| Var | Example | Default | |
|---|---|---|---|
GGUF_REPO | openbmb/MiniCPM5-2B-GGUF | required; openbmb/MiniCPM5-1B-GGUF also works | |
QUANT | Q4_K_M (1.56 GB, recommended) / Q8_0 (2.68 GB) / F16 (5.04 GB) | Q4_K_M | |
NGL | 99 (all layers on GPU) / 0 (CPU only) | 99 if NVIDIA GPU, else 0 | |
CTX | 8192 (default) up to 131072 (128 K) | 8192 |
Steps
1. Install llama.cpp
2. Download the GGUF
3a. Interactive chat (CLI)
3b. OpenAI-compatible HTTP server
4. Validate
Expected: "2" in the reply.
In llama.cpp, the default min_p=0.05 can lead to repetitive output: it filters out tokens whose probability is below 5% of the highest-probability token, potentially discarding the exact tokens needed to break out of a repetition loop. To prevent this, we set min_p=0.0.
Sampling defaults
| Mode | --temp | --top-p | --min-p | |
|---|---|---|---|---|
| MiniCPM5-2B Think | 1.0 | 0.95 | 0.0 | |
| MiniCPM5-1B Think | 0.9 | 0.95 | 0.0 | |
| MiniCPM5-1B No-think | 0.7 | 0.95 | 0.0 |
Choosing a quant
| Quant | Disk | Quality | |
|---|---|---|---|
| F16 | 5.04 GB | reference | |
| Q8_0 | 2.68 GB | ~indistinguishable from F16 | |
| Q4_K_M | 1.56 GB | small drop, ideal for laptops |
Common pitfalls
- Slow on CPU + large context: drop
-c 131072to-c 8192if you don't need 128 K.
Building your own GGUF (advanced)
If you've trained your own MiniCPM5-1B or MiniCPM5-2B variant, build a GGUF with:
Trained a LoRA adapter (not a full model) and want to apply it at runtime with --lora instead of baking it in? Convert it to a GGUF adapter — see `minicpm5-finetune-gguf-lora`.
When NOT to use
- NVIDIA GPU + want OpenAI-compatible serving →
minicpm5-deploy-vllm - Apple Silicon native →
minicpm5-deploy-mlxis faster - Just want one-line desktop run →
minicpm5-deploy-ollama - Want a desktop GUI →
minicpm5-deploy-lmstudio
Reference
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/minicpm5-deploy-llama-cpp/SKILL.md
Popularity
- Repository stars
- 9,518
- Repository forks
- 625
- 7-day trend score
- 46
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/openbmb/minicpm/minicpm5-deploy-llama-cpp)