Instructions to use WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

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

Install from pip and serve model

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

Use Docker

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

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

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf WhiskyAKM/MiniCPM5-2B-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": "WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-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 WhiskyAKM/MiniCPM5-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

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

WhiskyAKM commited on 3 days ago

Commit

6dca099

verified ·

1 Parent(s): 1ca3c18

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

.gitattributes +3 -0
README.md +22 -0
minicpm5-2b-dspark-Q4_K_M.gguf +3 -0
minicpm5-2b-dspark-Q8_0.gguf +3 -0
minicpm5-2b-dspark-bf16.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -41,3 +41,6 @@ minicpm5-2b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 minicpm5-2b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 minicpm5-2b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 minicpm5-2b-bf16.gguf filter=lfs diff=lfs merge=lfs -text

 minicpm5-2b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 minicpm5-2b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 minicpm5-2b-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+minicpm5-2b-dspark-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+minicpm5-2b-dspark-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+minicpm5-2b-dspark-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -49,6 +49,16 @@ MiniCPM5-2B is designed for local assistants, coding agents, tool-use workflows,
 | `minicpm5-2b-Q4_K_S.gguf`   | Q4_K_S       | 1.4 GB | Smaller, slight quality loss                    |
 | `minicpm5-2b-Q4_0.gguf`     | Q4_0         | 1.4 GB | Legacy 4-bit, broad compatibility               |
 ## Usage
 ### llama.cpp CLI
@@ -70,6 +80,17 @@ MiniCPM5-2B is designed for local assistants, coding agents, tool-use workflows,
 The GGUF also works with **Ollama** and **LM Studio**.
 ### Thinking Mode
 The model supports deep-thinking output. You can control it per request via the chat template, e.g. with an OpenAI-compatible API:
@@ -98,6 +119,7 @@ These GGUF files were created from the BF16 source model using `llama-quantize`
 ## Acknowledgements
 - Original model: [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B)
 - Quantization tool: [llama.cpp](https://github.com/ggml-org/llama.cpp)
 ## License

 | `minicpm5-2b-Q4_K_S.gguf`   | Q4_K_S       | 1.4 GB | Smaller, slight quality loss                    |
 | `minicpm5-2b-Q4_0.gguf`     | Q4_0         | 1.4 GB | Legacy 4-bit, broad compatibility               |
+### DSpark Draft Model (Speculative Decoding)
+| File                             | Quantization | Size  | Use Case                                        |
+| :------------------------------- | :----------- | :---- | :---------------------------------------------- |
+| `minicpm5-2b-dspark-bf16.gguf`   | BF16         | 623 MB | Draft model, full precision                     |
+| `minicpm5-2b-dspark-Q8_0.gguf`   | Q8_0         | 334 MB | Draft model, near-lossless                      |
+| `minicpm5-2b-dspark-Q4_K_M.gguf` | Q4_K_M       | 186 MB | Draft model, smallest footprint                 |
+These are the [MiniCPM5-2B-DSpark](https://huggingface.co/openbmb/MiniCPM5-2B-DSpark) draft models, trained for speculative decoding with MiniCPM5-2B. They accelerate generation without changing the target model's outputs.
 ## Usage
 ### llama.cpp CLI
 The GGUF also works with **Ollama** and **LM Studio**.
+### Speculative Decoding (DSpark)
+Pair the target model with a DSpark draft model to speed up inference. Draft model quality has minimal impact on output, so smaller quants (e.g. Q4_K_M) are usually fine:
+```bash
+./llama-server \
+  -m minicpm5-2b-Q4_K_M.gguf \
+  -md minicpm5-2b-dspark-Q4_K_M.gguf \
+  --host 0.0.0.0 --port 8080
+```
 ### Thinking Mode
 The model supports deep-thinking output. You can control it per request via the chat template, e.g. with an OpenAI-compatible API:
 ## Acknowledgements
 - Original model: [openbmb/MiniCPM5-2B](https://huggingface.co/openbmb/MiniCPM5-2B)
+- Draft model: [openbmb/MiniCPM5-2B-DSpark](https://huggingface.co/openbmb/MiniCPM5-2B-DSpark)
 - Quantization tool: [llama.cpp](https://github.com/ggml-org/llama.cpp)
 ## License

minicpm5-2b-dspark-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad0b44d4facfc422ececd107992562e09ded4912e5c4432256d872c02b40e48
+size 194103104

minicpm5-2b-dspark-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed1f40c1b346a94a504451acbfd7a01a6ec9aa9a87b4a5704c052beee5bd732
+size 349218624

minicpm5-2b-dspark-bf16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf18d0d5838ec2c92dc330f7ecc8c16dcc508ec1eb5e7a515f3b816a9c0c139
+size 652732224