Instructions to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU 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 ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0
# Run inference directly in the terminal:
llama cli -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0
# Run inference directly in the terminal:
llama cli -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

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 ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

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 ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

Use Docker

docker model run hf.co/ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

LM Studio
Jan

vLLM

How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProCreations/MiniCPM5-2B-Q8_0-WebGPU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProCreations/MiniCPM5-2B-Q8_0-WebGPU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

Ollama
How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with Ollama:
```
ollama run hf.co/ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0
```
Unsloth Desktop

How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

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": "ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with Docker Model Runner:
```
docker model run hf.co/ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0
```

Lemonade

How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

Run and chat with the model

lemonade run user.MiniCPM5-2B-Q8_0-WebGPU-Q8_0

List all available models

lemonade list

Hermes Agent

How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

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 ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ProCreations/MiniCPM5-2B-Q8_0-WebGPU with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0

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 "ProCreations/MiniCPM5-2B-Q8_0-WebGPU:Q8_0" \
  --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-Q8_0-WebGPU / README.md

ProCreations

Add verified lossless shards of official MiniCPM5-2B Q8_0 for WebGPU

0f58fbf verified 25 days ago

preview code

Raw History Blame Contribute Delete

1.11 kB

metadata

license: apache-2.0
base_model: openbmb/MiniCPM5-2B-GGUF
library_name: gguf
pipeline_tag: text-generation
tags:
  - webgpu
  - wllama
  - minicpm5
  - gguf
  - q8_0

MiniCPM5-2B · Q8_0 browser shards

A lossless GGUF split of OpenBMB's official MiniCPM5-2B-Q8_0.gguf. No re-quantization, pruning, conversion of tensor values, or changes to the model architecture. All 381 tensors were compared by SHA-256 against the original. See verification.json.

Split with llama-gguf-split --split-max-size 512M into six files, each under the browser's 2 GB ArrayBuffer limit. Pass the first shard URL to Wllama 3.6.1; it discovers and downloads the other five in parallel.

Chat and create files entirely in your browser: MiniCPM5 WebGPU

Model by OpenBMB. Browser experience by ProCreations. Original weights are Apache 2.0. Please refer to the upstream model card for model capabilities, training, and limitations.