Instructions to use ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ClankLabs/Wrench-9B-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClankLabs/Wrench-9B-Q4_K_M-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": "ClankLabs/Wrench-9B-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M

Ollama
How to use ClankLabs/Wrench-9B-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ClankLabs/Wrench-9B-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ClankLabs/Wrench-9B-Q4_K_M-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": "ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ClankLabs/Wrench-9B-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use ClankLabs/Wrench-9B-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Wrench-9B-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-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 ClankLabs/Wrench-9B-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ClankLabs/Wrench-9B-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ClankLabs/Wrench-9B-Q4_K_M-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 "ClankLabs/Wrench-9B-Q4_K_M-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"

Wrench 9B — Purpose-Built Agentic Model

A LoRA fine-tuned version of Qwen3.5-9B (dense), purpose-built for tool calling, error recovery, and system prompt following. Runs on 8GB VRAM.

Part of the Wrench family — the 35B sibling scores 82% on the Berkeley Function Calling Leaderboard (BFCL).

Benchmarks

Benchmark	Score	Details
Clank Agentic Benchmark	114/120 (95%)	40-prompt, 8-category tool-calling evaluation

Category Breakdown

Category	Score	Max
Basic Tool Use	15	15
Multi-Step Tasks	15	15
Error Recovery	14	15
Response Quality	14	15
System Prompt Following	15	15
Planning & Reasoning	15	15
Tool Format Correctness	15	15
Safety & Restraint	15	15
Total	114	120

vs. Frontier Models

Model	Score	Runs On	Cost
Wrench 35B v7	118/120 + 82% BFCL	16GB GPU	Free
Claude Sonnet 4.6	~114/120	Cloud	$20/mo
Wrench 9B v4	114/120	8GB GPU	Free
GPT-4o	~110/120	Cloud	$20/mo
Claude Haiku	~100/120	Cloud	Paid
Base Qwen 3.5 9B	~50/120	8GB GPU	Free

Quick Start

Ollama (recommended)

Download the GGUF and Modelfile from the Files tab, then:

ollama create wrench-9b -f Modelfile
ollama run wrench-9b

llama.cpp

./llama-server -m wrench-9B-Q4_K_M.gguf --jinja -ngl 100 -fa on \
  --temp 0.4 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 8192

With Clank Gateway

npm install -g @clanklabs/clank
clank setup
# Set primary model to "ollama/wrench-9b" in config

Model Details


Base Model	Qwen3.5-9B (dense)
Fine-Tune Method	LoRA (rank 32, alpha 64) via HuggingFace PEFT
Training Data	1,356 examples across 15 categories
Hardware	1x NVIDIA H100 80GB
Training Time	~30 minutes
Final Loss	0.1512
Quantization	Q4_K_M GGUF (~5GB)
Context Window	8,192 tokens
License	Apache 2.0

Training Data

All training data is published and auditable: ClankLabs/wrench-training-data

1,356 examples (1,251 base + 105 frontier-targeted) across 15 categories.

Model tree for ClankLabs/Wrench-9B-Q4_K_M-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(522)

this model

ClankLabs
/

Wrench-9B-Q4_K_M-GGUF

Wrench 9B — Purpose-Built Agentic Model

Benchmarks

Category Breakdown

vs. Frontier Models

Quick Start

Ollama (recommended)

llama.cpp

With Clank Gateway

Model Details

Training Data

Links

Model tree for ClankLabs/Wrench-9B-Q4_K_M-GGUF