Instructions to use 3amthoughts/zenfinance-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use 3amthoughts/zenfinance-3b with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use 3amthoughts/zenfinance-3b 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 3amthoughts/zenfinance-3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 3amthoughts/zenfinance-3b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 3amthoughts/zenfinance-3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf 3amthoughts/zenfinance-3b: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 3amthoughts/zenfinance-3b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 3amthoughts/zenfinance-3b: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 3amthoughts/zenfinance-3b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 3amthoughts/zenfinance-3b:Q4_K_M

Use Docker

docker model run hf.co/3amthoughts/zenfinance-3b:Q4_K_M

LM Studio
Jan

vLLM

How to use 3amthoughts/zenfinance-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "3amthoughts/zenfinance-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "3amthoughts/zenfinance-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/3amthoughts/zenfinance-3b:Q4_K_M

Ollama
How to use 3amthoughts/zenfinance-3b with Ollama:
```
ollama run hf.co/3amthoughts/zenfinance-3b:Q4_K_M
```
Unsloth Desktop

How to use 3amthoughts/zenfinance-3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 3amthoughts/zenfinance-3b: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": "3amthoughts/zenfinance-3b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 3amthoughts/zenfinance-3b with Docker Model Runner:
```
docker model run hf.co/3amthoughts/zenfinance-3b:Q4_K_M
```

Lemonade

How to use 3amthoughts/zenfinance-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 3amthoughts/zenfinance-3b:Q4_K_M

Run and chat with the model

lemonade run user.zenfinance-3b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use 3amthoughts/zenfinance-3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 3amthoughts/zenfinance-3b: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 3amthoughts/zenfinance-3b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 3amthoughts/zenfinance-3b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 3amthoughts/zenfinance-3b: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 "3amthoughts/zenfinance-3b: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"

zenfinance-3b / README.md

3amthoughts

Upload README.md with huggingface_hub

5ecdff7 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

1.98 kB

	---
	base_model: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
	library_name: peft
	license: apache-2.0
	tags:
	- finance
	- agent
	- tool-calling
	- unsloth
	- gguf
	- llama-3
	- reasoning
	language:
	- en
	pipeline_tag: text-generation
	---
	<p align="center">
	<img src="https://huggingface.co/3amthoughts/zenfinance-3b/resolve/main/post-136-hd.png" width="800">
	</p>



	# 🧘‍♂️ ZenFinance-3B-Agent (GGUF)

	ZenFinance-3B is a highly specialized, agentic large language model designed for personal finance applications. Fine-tuned from Llama-3.2-3B-Instruct, this model acts as both a financial advisor and a UI agent.

	It is trained to "think" before it speaks using `<thought>` tags, and can execute frontend actions (like adding expenses or setting savings goals) by outputting strict JSON inside `<tool_call>` tags.

	## ⚡ Model Highlights
	* Architecture: 3B Parameters (Llama-3.2 base)
	* Format: GGUF (`q4_k_m` - highly compressed, runs on <3GB RAM)
	* Capabilities: Financial reasoning, budgeting advice, and structured JSON tool calling.
	* Training: Fine-tuned using QLoRA via [Unsloth](https://github.com/unslothai/unsloth) on a mixed dataset of 4,000 financial and agentic interactions.

	---

	## 🛠️ How it Works (Prompting & Output)

	To get the model to trigger actions, you must use the standard Llama-3 chat template and include the system prompt defining its tools.

	System Prompt:
	> "You are ZenFinance AI, a minimalist personal finance assistant. You provide calm, objective financial advice and can execute actions using tools."

	### Example Interaction

	User:
	> "I just spent $12 on lunch."

	ZenFinance-3B Output:
	```text
	<thought>
	User spent $12 on lunch. Category: Food. This is an expense.
	I will trigger the add_transaction tool to update their dashboard.
	</thought>
	<tool_call>
	{"action": "add_transaction", "amount": 12, "category": "Food", "type": "expense"}
	</tool_call>
	I've added that $12 food expense to your dashboard.