Instructions to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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": "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M

SGLang

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with Ollama:
```
ollama run hf.co/mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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": "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 "mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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"

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic.f16.gguf filter=lfs diff=lfs merge=lfs -text

mradermacher
/

MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF

uploaded from rich1

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e63b407d0476b3c5f853ec9fc9f994571abe813c3e293664fba7e7c8bc4ccff
+size 1433339936

+version https://git-lfs.github.com/spec/v1
+oid sha256:a35efe52f5b8d7bd28de9ea8037099cfebba0d25ed31545c540bec3b0c513f17
+size 1039927328

+version https://git-lfs.github.com/spec/v1
+oid sha256:b87b8ec4675ea666e089b84fd338ff1c62d2ebd7632ca0e8f93862c7faf3e34d
+size 1378977824

+version https://git-lfs.github.com/spec/v1
+oid sha256:5138d8beca2e4218ea5567074f84f5b3ab4d62de4da0d5a13b4d6907591c87fe
+size 1291421728

+version https://git-lfs.github.com/spec/v1
+oid sha256:da55906ac222d3aa5ae11771d711b2fb405cade39913114368f356cba1be9024
+size 1191634976

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c01dcfe517866d1fadd93b9de53e67d0fd438dcf1d396166504103246857543
+size 1561319456

+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cf33068541fc9f2397a58a5e289aade7b4cc1d9b60f4141ca5a1a2a5d1ae56
+size 1498482720

+version https://git-lfs.github.com/spec/v1
+oid sha256:bfcb9961ab4b9b2df18b579bcf4d2d86e72f78220a1684ea4efbd8ab96a5f759
+size 1808062496

+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b280f83355e976e6b495f1870c94c344d054f7d4bea0a0dde1cd6ddbae147f
+size 1771505696

+version https://git-lfs.github.com/spec/v1
+oid sha256:72acf70115f030d90da7cfac98143e7a41d6e41ec11c05b707c9c185edb0d2ab
+size 2070226976

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

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

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

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3d243af36cc84c775ecd50b9c9ffab94e13142027fbaba18a676e12a0067a3
+size 2679711776

+version https://git-lfs.github.com/spec/v1
+oid sha256:09ce7d92ab9fdf06bb8ca2ab25740f710821b79aab2947159ce1a223113d39b4
+size 5039007776