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

Libraries

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF",
	filename="MiniCPM5-1B-Claude-Opus-Fable5-Thinking-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

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

Use Docker

docker model run hf.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF:Q4_K_M

Ollama
How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with Ollama:
```
ollama run hf.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF:Q4_K_M
```

Unsloth Studio

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF to start chatting

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-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 GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-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 GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with OpenClaw:

Start the llama.cpp server

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

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

Lemonade

How to use GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF / README-cn.md

GnLOLot

update readme

5a4ed2c verified about 24 hours ago

preview code

Raw

History Blame Contribute Delete

3.68 kB

metadata

license: apache-2.0
base_model: GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking
base_model_relation: quantized
language:
  - en
  - zh
pipeline_tag: text-generation
library_name: gguf
tags:
  - gguf
  - llama.cpp
  - quantized
  - minicpm5
  - thinking
  - fable5
  - coding
  - instruction-following

MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF

📢 V2.0 已发布 — 我们已发布增强 工具调用 能力的新版本，欢迎通过以下链接下载体验：

Transformers：MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking

GGUF：MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF

MiniCPM5-1B-Claude-Opus-Fable5-Thinking 的 GGUF 量化版，适用于 llama.cpp、Ollama、LM Studio、jan、KoboldCpp 等运行时。

Transformers 版见 MiniCPM5-1B-Claude-Opus-Fable5-Thinking

English README

本仓库提供基于 openbmb/MiniCPM5-1B、经 Fable 5 数据微调的 1B Thinking 模型的本地部署版本。GGUF 文件内嵌 MiniCPM5 原生对话模板，可直接用于 llama.cpp 生态。

文件列表

文件	量化	大小	说明
`MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q4_K_M.gguf`	Q4_K_M	~657 MB	体积最小
`MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q5_K_M.gguf`	Q5_K_M	~751 MB	质量/体积均衡
`MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q8_0.gguf`	Q8_0	~1.1 GB	推荐默认
`MiniCPM5-1B-Claude-Opus-Fable5-Thinking-F16.gguf`	F16	~2.1 GB	全精度转换底稿

对该 1B 模型，Q8_0 为推荐默认量化版本。

快速开始

llama-cli \
  -m MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q8_0.gguf \
  -p "写一个 Python 函数，合并两个有序链表。" \
  -n 512 \
  --temp 0.9 --top-p 0.95 \
  -c 8192

模型理论上下文为 128K tokens（config.json 中 max_position_embeddings = 131072）。实际可用长度请根据显存/内存调整 -c 参数。

采样建议

生成参数继承自 **MiniCPM5-1B**：

模式	参数
Think（默认）	`temperature=0.9, top_p=0.95`
No Think	`temperature=0.7, top_p=0.95`，`enable_thinking=False`

能力

Fable 5 微调 — 使用 Fable 5 数据后训练
Coding — 代码生成、调试及软件工程工作流
Instruction Following — 更稳定地遵循用户指令与任务约束
Thinking 模式 — 思维链推理；GGUF 内嵌 MiniCPM5 对话模板
长上下文 — 最高 128K tokens（上游 config.json 为 131,072）

局限性

Thinking 输出 — 模型可能在最终回答前输出推理块
1B 体量 — 面向轻量本地部署
运行时限制 — 实际可用上下文取决于 GGUF 运行时与硬件配置

许可

Apache-2.0（继承 MiniCPM5-1B）

致谢

基座：OpenBMB / MiniCPM5-1B
Transformers 版：MiniCPM5-1B-Claude-Opus-Fable5-Thinking
量化：llama.cpp