Instructions to use Caldalis/MiniCPM5-2B-Math-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Caldalis/MiniCPM5-2B-Math-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 Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Caldalis/MiniCPM5-2B-Math-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 Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Caldalis/MiniCPM5-2B-Math-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Caldalis/MiniCPM5-2B-Math-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": "Caldalis/MiniCPM5-2B-Math-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

Ollama
How to use Caldalis/MiniCPM5-2B-Math-GGUF with Ollama:
```
ollama run hf.co/Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Caldalis/MiniCPM5-2B-Math-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Caldalis/MiniCPM5-2B-Math-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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Caldalis/MiniCPM5-2B-Math-GGUF with Docker Model Runner:
```
docker model run hf.co/Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M
```

Lemonade

How to use Caldalis/MiniCPM5-2B-Math-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM5-2B-Math-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Caldalis/MiniCPM5-2B-Math-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 Caldalis/MiniCPM5-2B-Math-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://127.0.0.1:8080/v1
hermes config set model.default Caldalis/MiniCPM5-2B-Math-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Caldalis/MiniCPM5-2B-Math-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Caldalis/MiniCPM5-2B-Math-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://127.0.0.1:8080/v1 \
  --custom-model-id "Caldalis/MiniCPM5-2B-Math-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"

MiniCPM5-2B-Math-GGUF / README.md

Caldalis

Add Chinese model card and sync English card

8f99d92 verified 7 days ago

preview code

Raw History Blame Contribute Delete

3.36 kB

	---
	license: apache-2.0
	language:
	- en
	- zh
	library_name: gguf
	pipeline_tag: text-generation
	base_model: Caldalis/MiniCPM5-2B-Math
	base_model_relation: quantized
	tags:
	- minicpm
	- minicpm5
	- math
	- reasoning
	- theorem-proving
	- gguf
	- llama.cpp
	---

	<div align="center">
	<img src="https://huggingface.co/Caldalis/MiniCPM5-2B-Math/resolve/main/assets/banner.png" alt="MiniCPM5-2B-Math: a 2.5B model for math and proofs, with a proof swarm you can run yourself" width="100%" />
	</div>

	<p align="center">
	English \|
	<a href="https://huggingface.co/Caldalis/MiniCPM5-2B-Math-GGUF/blob/main/README-cn.md" target="_blank">中文</a>
	</p>

	# MiniCPM5-2B-Math-GGUF

	GGUF builds of [MiniCPM5-2B-Math](https://huggingface.co/Caldalis/MiniCPM5-2B-Math), a 2.5B math and proof
	specialist, for llama.cpp, Ollama and LM Studio. Pair it with the
	[MiniCPM-Math Harness](https://github.com/Caldalis/MiniCPM-Math-harness) to run a small proof swarm on a laptop.

	\| File \| Size \| Notes \|
	\|---\|---:\|---\|
	\| `MiniCPM5-2B-Math-Q4_K_M.gguf` \| 1.6 GB \| smallest; quality loss likely on long proofs \|
	\| `MiniCPM5-2B-Math-Q8_0.gguf` \| 2.7 GB \| recommended: usually close to BF16, and used for our laptop tests \|
	\| `MiniCPM5-2B-Math-BF16.gguf` \| 5.0 GB \| full precision \|

	Converted with llama.cpp b10964 (`convert_hf_to_gguf.py`, tokenizer pre-type `minicpm5`) and quantized with
	`llama-quantize`. The recommended sampling settings (temperature 0.9, top-p 0.95, min-p 0, top-k off) are embedded in
	the GGUF metadata, so llama.cpp uses them by default. All results on the
	[model card](https://huggingface.co/Caldalis/MiniCPM5-2B-Math) were measured with the BF16 safetensors on vLLM.

	\| File \| SHA-256 \|
	\|---\|---\|
	\| `MiniCPM5-2B-Math-Q4_K_M.gguf` \| `9ff4f86fd8eb3a16b1ff6b29d86366f3c963320e44a7325e6fb90c0142a7cf0b` \|
	\| `MiniCPM5-2B-Math-Q8_0.gguf` \| `db251717a4d11b3221e7e2f1d096c3aebec94b1f25e8e24b4ebc56c185d32b9d` \|
	\| `MiniCPM5-2B-Math-BF16.gguf` \| `0703334ee732e110ef18dee427a8736fae52fbdd8a6ce3510de0df45dcaac72c` \|

	## llama.cpp

	```bash
	llama-server -hf Caldalis/MiniCPM5-2B-Math-GGUF:Q8_0 --jinja -ngl 99 -c 98304 -np 4 -kvu --port 8000
	```

	- `--jinja` uses the embedded chat template (thinking mode, `<think>` … `</think>`).
	- `-np 4 -kvu` gives 4 parallel slots that share a 96K-token KV cache: one slot per agent for the harness. Run the
	harness with `--profile quick` against this server.
	- `--port 8000` is where the harness looks by default; without it, `llama-server` listens on 8080.
	- The embedded defaults already set `min_p=0`; llama.cpp's usual 0.05 can encourage repetition with this model.

	## Ollama

	```bash
	ollama run hf.co/Caldalis/MiniCPM5-2B-Math-GGUF:Q8_0
	```

	Start the server with a larger context window (for example `OLLAMA_CONTEXT_LENGTH=65536 ollama serve`), because
	proofs routinely need tens of thousands of tokens. With the harness, pass
	`--base-url http://127.0.0.1:11434/v1 --model hf.co/Caldalis/MiniCPM5-2B-Math-GGUF:Q8_0 --no-raw`.

	## Recommended settings

	`temperature=0.9, top_p=0.95, min_p=0.0`, thinking enabled, and a large `max_tokens`. The published benchmark
	numbers let every call use the full 131,072-token context: a quarter of HMMT samples think past 64K tokens, and many
	of those still end with the right answer. On a laptop, 16K–32K is a practical compromise.

	## License

	Apache-2.0 (see `LICENSE`).