Instructions to use turnercore/functiongemma-automaticity-v7-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use turnercore/functiongemma-automaticity-v7-q8 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="turnercore/functiongemma-automaticity-v7-q8",
	filename="FunctionGemma_AUTOMATICITY_V7_Q8.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use turnercore/functiongemma-automaticity-v7-q8 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 turnercore/functiongemma-automaticity-v7-q8
# Run inference directly in the terminal:
llama cli -hf turnercore/functiongemma-automaticity-v7-q8

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf turnercore/functiongemma-automaticity-v7-q8
# Run inference directly in the terminal:
llama cli -hf turnercore/functiongemma-automaticity-v7-q8

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 turnercore/functiongemma-automaticity-v7-q8
# Run inference directly in the terminal:
./llama-cli -hf turnercore/functiongemma-automaticity-v7-q8

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 turnercore/functiongemma-automaticity-v7-q8
# Run inference directly in the terminal:
./build/bin/llama-cli -hf turnercore/functiongemma-automaticity-v7-q8

Use Docker

docker model run hf.co/turnercore/functiongemma-automaticity-v7-q8

LM Studio
Jan
Ollama
How to use turnercore/functiongemma-automaticity-v7-q8 with Ollama:
```
ollama run hf.co/turnercore/functiongemma-automaticity-v7-q8
```

Unsloth Studio

How to use turnercore/functiongemma-automaticity-v7-q8 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 turnercore/functiongemma-automaticity-v7-q8 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 turnercore/functiongemma-automaticity-v7-q8 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for turnercore/functiongemma-automaticity-v7-q8 to start chatting

How to use turnercore/functiongemma-automaticity-v7-q8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf turnercore/functiongemma-automaticity-v7-q8

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": "turnercore/functiongemma-automaticity-v7-q8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use turnercore/functiongemma-automaticity-v7-q8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf turnercore/functiongemma-automaticity-v7-q8

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 turnercore/functiongemma-automaticity-v7-q8

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use turnercore/functiongemma-automaticity-v7-q8 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf turnercore/functiongemma-automaticity-v7-q8

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 "turnercore/functiongemma-automaticity-v7-q8" \
  --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 turnercore/functiongemma-automaticity-v7-q8 with Docker Model Runner:
```
docker model run hf.co/turnercore/functiongemma-automaticity-v7-q8
```

Lemonade

How to use turnercore/functiongemma-automaticity-v7-q8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull turnercore/functiongemma-automaticity-v7-q8

Run and chat with the model

lemonade run user.functiongemma-automaticity-v7-q8-{{QUANT_TAG}}

List all available models

lemonade list

functiongemma-automaticity-v7-q8 / README.md

turnercore

Upload FunctionGemma AUTOMATICITY_V7_Q8 winner

85d6689 verified 7 days ago

preview code

Raw

History Blame Contribute Delete

795 Bytes

	---
	license: other
	base_model: google/functiongemma-270m-it
	tags:
	- function-calling
	- tool-use
	- automaticity
	- gguf
	---

	# FunctionGemma Automaticity V7 Q8

	Current automaticity benchmark winner. Public GGUF artifact retained as the comparison baseline for MiniCPM V8.

	The benchmark rows/results are stored in private dataset repo `turnercore/automaticity-benchmark-v1`; this model card includes the headline score.

	## Automaticity benchmark v1

	\| Run \| Exact \| Tool name \| Arguments \| No-op recall \| p50 latency \| p95 latency \|
	\| --- \| ---: \| ---: \| ---: \| ---: \| ---: \| ---: \|
	\| FunctionGemma_AUTOMATICITY_V7_Q8 \| 82/92 (89.1%) \| 96.7% \| 90.2% \| 94.7% \| 180 ms \| 568 ms \|

	This model remains the local winner until a later automaticity dataset/model beats it on the same frozen benchmark.