Instructions to use victor/functiongemma-agent-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use victor/functiongemma-agent-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="victor/functiongemma-agent-gguf",
	filename="functiongemma-270m-it.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use victor/functiongemma-agent-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf victor/functiongemma-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf victor/functiongemma-agent-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf victor/functiongemma-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf victor/functiongemma-agent-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 victor/functiongemma-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf victor/functiongemma-agent-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 victor/functiongemma-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf victor/functiongemma-agent-gguf:Q4_K_M

Use Docker

docker model run hf.co/victor/functiongemma-agent-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use victor/functiongemma-agent-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "victor/functiongemma-agent-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": "victor/functiongemma-agent-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/victor/functiongemma-agent-gguf:Q4_K_M

Ollama
How to use victor/functiongemma-agent-gguf with Ollama:
```
ollama run hf.co/victor/functiongemma-agent-gguf:Q4_K_M
```

Unsloth Studio new

How to use victor/functiongemma-agent-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 victor/functiongemma-agent-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 victor/functiongemma-agent-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for victor/functiongemma-agent-gguf to start chatting

Pi new

How to use victor/functiongemma-agent-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf victor/functiongemma-agent-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": "victor/functiongemma-agent-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use victor/functiongemma-agent-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf victor/functiongemma-agent-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 victor/functiongemma-agent-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use victor/functiongemma-agent-gguf with Docker Model Runner:
```
docker model run hf.co/victor/functiongemma-agent-gguf:Q4_K_M
```

Lemonade

How to use victor/functiongemma-agent-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull victor/functiongemma-agent-gguf:Q4_K_M

Run and chat with the model

lemonade run user.functiongemma-agent-gguf-Q4_K_M

List all available models

lemonade list

FunctionGemma Agent GGUF

A fine-tuned version of FunctionGemma-270M for agentic tool-calling tasks, converted to GGUF format for use with llama.cpp and llama-agent.

Model Details

Property	Value
Base Model	unsloth/functiongemma-270m-it
Fine-tuned Model	victor/functiongemma-agent-finetuned
Training Dataset	victor/functiongemma-agent-sft
Quantization	Q4_K_M (4-bit)
Parameters	270M

Training

Fine-tuned using Unsloth with LoRA on HuggingFace Jobs infrastructure.

Training Configuration:

LoRA rank: 128, alpha: 256
Epochs: 3
Learning rate: 2e-4
Batch size: 4, gradient accumulation: 2
Hardware: NVIDIA A100-80GB
Training method: SFT with train_on_responses_only

Dataset: 7,500 synthetic examples covering:

Multi-step tool chaining (glob → read → edit)
Error recovery patterns
Clarification dialogs
No-tool responses
Parallel tool calls

Tools

The model is trained on 5 tools matching llama-agent:

Tool	Description
`read_file`	Read file contents with line numbers
`write_file`	Create or overwrite a file
`edit_file`	Find and replace text in a file
`glob`	Find files matching pattern
`bash`	Execute shell command

Usage

With llama.cpp

# Download
wget https://huggingface.co/victor/functiongemma-agent-gguf/resolve/main/functiongemma-270m-it.Q4_K_M.gguf

# Run inference
./llama-cli -m functiongemma-270m-it.Q4_K_M.gguf -p "<start_of_turn>user
Read the main.py file
<end_of_turn>
<start_of_turn>model"

With llama-agent

./llama-agent -m functiongemma-270m-it.Q4_K_M.gguf

Format

Uses FunctionGemma's native format with <escape> delimiters:

<start_of_turn>user
Fix the typo in config.json
<end_of_turn>
<start_of_turn>model
<think>I need to find and read the config file first.</think>
<start_function_call>call:glob{pattern:<escape>**/config.json<escape>}<end_function_call>
<end_of_turn>
<start_of_turn>developer
<start_function_response>response:glob{stdout:<escape>src/config.json<escape>,stderr:<escape><escape>,exit_code:0}<end_function_response>
<end_of_turn>
...

License

This model inherits the Gemma license from the base model.

Model tree for victor/functiongemma-agent-gguf

Base model

google/functiongemma-270m-it

Finetuned

unsloth/functiongemma-270m-it

Quantized

(8)

this model

victor
/

functiongemma-agent-gguf