Instructions to use tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use tpnlabs/MiniCPM5-1B-TPN-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tpnlabs/MiniCPM5-1B-TPN-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": "tpnlabs/MiniCPM5-1B-TPN-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M

Ollama
How to use tpnlabs/MiniCPM5-1B-TPN-GGUF with Ollama:
```
ollama run hf.co/tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M
```
Unsloth Desktop

How to use tpnlabs/MiniCPM5-1B-TPN-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tpnlabs/MiniCPM5-1B-TPN-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": "tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tpnlabs/MiniCPM5-1B-TPN-GGUF with Docker Model Runner:
```
docker model run hf.co/tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M
```

Lemonade

How to use tpnlabs/MiniCPM5-1B-TPN-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM5-1B-TPN-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-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 tpnlabs/MiniCPM5-1B-TPN-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tpnlabs/MiniCPM5-1B-TPN-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tpnlabs/MiniCPM5-1B-TPN-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 "tpnlabs/MiniCPM5-1B-TPN-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"

MiniCPM5-1B · TPN-optimised GGUF

Quantised and measured by TPN Workbench from openbmb/MiniCPM5-1B @ 87179e5. Every format is scored against the BF16 reference on next-token KL divergence, perplexity and top-1 agreement (llama.cpp b11528).

Full report: https://bench.trueperformancenetwork.com/r/AK3RgkmOPXqaNB4xGCJ_XQ

TPN recommendation: Q5_0+: Highest-fidelity format that fits 0.8 GB: 0.775 GB, closeness 0.017.

Files

file	format	size	mean KLD	KL similarity	PPL Δ	top-1
`MiniCPM5-1B-Q5_0-tuned.gguf`	Q5_0+	0.77 GB	0.0166	98.4 %	+1.27 %	93.0 %	TPN recommendation
`MiniCPM5-1B-Q4_K_M.gguf`	Q4_K_M	0.69 GB	0.0865	91.7 %	+6.56 %	84.9 %
`MiniCPM5-1B-Q8_0.gguf`	Q8_0	1.15 GB	0.0018	99.8 %	+0.20 %	97.6 %

Q5_0+ is a TPN fidelity-tuned format: starting from Q5_0, TPN picks each tensor's quantisation type by measurement, keeping the file small while staying closer to the original than the plain format.

Lower KLD = closer to the original. K-quants (Q4_K_M, Q8_0) have SIMD kernels in llama.cpp WebAssembly, so they are the faster pick in the browser; IQ* formats are smallest-for-quality on native CPU/GPU builds.

Measurements

format	size	bpw	mean KLD	PPL Δ	top-1
Q8_0	1.15 GB	8.5	0.0018	+0.20 %	97.6 %
Q5_0	0.90 GB	5.5	0.0343	+1.69 %	90.1 %
Q4_0M+	0.84 GB	4.81	0.0456	+1.91 %	88.8 %
Q4_0	0.81 GB	4.5	0.1402	+10.48 %	80.7 %
Q5_0+	0.77 GB	5.5	0.0166	+1.27 %	93.0 %
Q4_K_M	0.69 GB	4.77	0.0865	+6.56 %	84.9 %
IQ4_XS	0.64 GB	4.27	0.1006	+7.35 %	83.3 %
Q3_K_M	0.58 GB	3.85	0.2653	+23.47 %	74.1 %
Q2_K	0.49 GB	2.94	1.1923	+183.09 %	50.4 %

Task benchmarks

Score in %, change vs BF16 in points.

format	gsm8k	ifeval
BF16	40.9	37.9
Q5_0+	38.1 (-2.7)	38.4 (+0.5)
Q4_K_M	30.0 (-10.8)	36.9 (-1.0)

Use

llama-server -hf tpnlabs/MiniCPM5-1B-TPN-GGUF --hf-file MiniCPM5-1B-Q5_0-tuned.gguf

Runs fully on-device in Gratis, in the browser or desktop app.

Licence: inherited from the base model (apache-2.0).

Downloads last month: -

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for tpnlabs/MiniCPM5-1B-TPN-GGUF

Base model

openbmb/MiniCPM5-1B

Quantized

(101)

this model