Instructions to use BrinqAI/smartpanel-functiongemma-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BrinqAI/smartpanel-functiongemma-270m with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BrinqAI/smartpanel-functiongemma-270m",
	filename="smartpanel-v12-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 BrinqAI/smartpanel-functiongemma-270m with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BrinqAI/smartpanel-functiongemma-270m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BrinqAI/smartpanel-functiongemma-270m:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BrinqAI/smartpanel-functiongemma-270m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BrinqAI/smartpanel-functiongemma-270m: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 BrinqAI/smartpanel-functiongemma-270m:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BrinqAI/smartpanel-functiongemma-270m: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 BrinqAI/smartpanel-functiongemma-270m:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BrinqAI/smartpanel-functiongemma-270m:Q4_K_M

Use Docker

docker model run hf.co/BrinqAI/smartpanel-functiongemma-270m:Q4_K_M

LM Studio
Jan

vLLM

How to use BrinqAI/smartpanel-functiongemma-270m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BrinqAI/smartpanel-functiongemma-270m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BrinqAI/smartpanel-functiongemma-270m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BrinqAI/smartpanel-functiongemma-270m:Q4_K_M

Ollama
How to use BrinqAI/smartpanel-functiongemma-270m with Ollama:
```
ollama run hf.co/BrinqAI/smartpanel-functiongemma-270m:Q4_K_M
```

Unsloth Studio new

How to use BrinqAI/smartpanel-functiongemma-270m 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 BrinqAI/smartpanel-functiongemma-270m 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 BrinqAI/smartpanel-functiongemma-270m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BrinqAI/smartpanel-functiongemma-270m to start chatting

Pi new

How to use BrinqAI/smartpanel-functiongemma-270m with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BrinqAI/smartpanel-functiongemma-270m: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": "BrinqAI/smartpanel-functiongemma-270m:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BrinqAI/smartpanel-functiongemma-270m with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BrinqAI/smartpanel-functiongemma-270m: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 BrinqAI/smartpanel-functiongemma-270m:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use BrinqAI/smartpanel-functiongemma-270m with Docker Model Runner:
```
docker model run hf.co/BrinqAI/smartpanel-functiongemma-270m:Q4_K_M
```

Lemonade

How to use BrinqAI/smartpanel-functiongemma-270m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BrinqAI/smartpanel-functiongemma-270m:Q4_K_M

Run and chat with the model

lemonade run user.smartpanel-functiongemma-270m-Q4_K_M

List all available models

lemonade list

SmartPanel FunctionGemma 270M

Fine-tuned FunctionGemma 270M for on-device function-calling inside Brinq's SmartPanel manufacturing-assistant demo. Shipped on the Synaptics Astra SL2619 SoC (2×Cortex-A55 @ 2 GHz, 1 TOPS Torq/Coral NPU, 2 GB DDR4) at Embedded World 2026.

What this model does

Given a user utterance and a list of tool declarations, the model emits one or more <start_function_call>call:NAME{...}<end_function_call> blocks or a plain natural-language reply. It was trained specifically to hit sub-500 ms decode latency on the SL2619 without giving up tool-selection accuracy on the SmartPanel domain.

Scope. The fine-tune is specific to the SmartPanel tool schema (maintenance procedures, alarm acknowledgement, photo capture, knowledge lookup). It's published here as prior art / starting checkpoint for the related Coral Dev Board physical-AI demo at Google IO 2026, not as a general-purpose function-calling model.

Files

File	Format	Size	Recommended use
`smartpanel-v15-q4_k_m.gguf`	GGUF Q4_K_M	253 MB	Production. Runs via llama.cpp on 2 GB / 2-core ARM targets.
`smartpanel-v15-f16.gguf`	GGUF F16	543 MB	Canonical checkpoint for re-quantization or further fine-tuning.
`smartpanel-v12-q4_k_m.gguf`	GGUF Q4_K_M	253 MB	Mid-production milestone.
`smartpanel-v8-q4_k_m.gguf`	GGUF Q4_K_M	253 MB	Device deployment milestone (what our SL2619 test boards have shipped with since Feb).
`smartpanel-v4-q4_k_m.gguf`	GGUF Q4_K_M	253 MB	First version with correct `call:` output format. Benchmark reference.

Recommended starting point: smartpanel-v15-q4_k_m.gguf.

Version lineage

Version	Date	Format	Notes
v4	2026-01-18	`call:`	First correct output format. 84.2% domain accuracy, 142 ms avg latency on local llama-cpp.
v8	2026-02-24	`call:`	Deployed to Ollama on SL2619 test boards.
v8-moveworks	2026-02-26	`call:`	Variant trained with additional Moveworks-flavored examples. Not included here.
v8-fixed	2026-02-27	`call:`	Tokenizer hotfix.
v9–v13	Feb 27 – Mar 1	`call:`	Data curation + prompt-template iterations.
v15	2026-03-03	`call:`	Current production.

(v14 was trained but rolled forward into v15 before quantization — no separate artifact exists.)

Prompt format

FunctionGemma's native format. The tokenizer ships the <start_function_call>, <end_function_call>, <start_function_declaration>, <end_function_declaration>, <start_function_response>, <end_function_response>, and <start_of_turn> / <end_of_turn> special tokens.

<start_of_turn>user
You are a model that can do function calling with the following functions

<start_function_declaration>
declaration:set_led_color{description:<escape>Set RGB LED color<escape>,parameters:{...}}
<end_function_declaration>
<start_function_declaration>
declaration:play_buzzer{description:<escape>Sound the buzzer<escape>,parameters:{...}}
<end_function_declaration>

Turn the lights red and beep
<end_of_turn>
<start_of_turn>model
<start_function_call>call:set_led_color{color:<escape>red<escape>}<end_function_call><start_function_call>call:play_buzzer{pattern:<escape>beep<escape>}<end_function_call>
<end_of_turn>

Stop tokens: <end_of_turn>, <end_function_call>, <eos>. Recommended generation params: temperature=0.1, top_p=0.9, num_ctx=2048.

Usage

llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="smartpanel-v15-q4_k_m.gguf",
    n_ctx=1024,
    n_threads=2,
    verbose=False,
)

prompt = """<start_of_turn>user
You are a model that can do function calling with the following functions
<start_function_declaration>
declaration:acknowledge_alarm{description:<escape>Dismiss the current alarm<escape>,parameters:{properties:{},required:[],type:<escape>OBJECT<escape>}}
<end_function_declaration>

Ack the alarm
<end_of_turn>
<start_of_turn>model
"""

out = llm(prompt, max_tokens=128, temperature=0.1, stop=["<end_of_turn>"])
print(out["choices"][0]["text"])

Ollama

# Download the gguf, then:
cat > Modelfile <<'EOF'
FROM ./smartpanel-v15-q4_k_m.gguf
PARAMETER temperature 0.1
PARAMETER num_ctx 2048
PARAMETER stop "<end_of_turn>"
PARAMETER stop "<end_function_call>"
PARAMETER stop "<eos>"
EOF

ollama create smartpanel -f Modelfile
ollama run smartpanel "Ack the alarm"

Benchmark (v3 / pre-v15, Jan 2026)

On SmartPanel domain (llama-cpp-python, Q4_K_M, local dev machine):

Model	Domain	Accuracy	Avg Latency	Output Format
Mobile Actions base	mobile	100 %	178 ms	`call:`
SmartPanel v1	smartpanel	66.7 %	355 ms	❌ `declaration:`
SmartPanel v2	smartpanel	36.8 %	135 ms	❌ partial output
SmartPanel v3 (precursor to v4)	smartpanel	84.2 %	142 ms	✅ `call:`
Mobile Actions (cross-domain)	smartpanel	66.7 %	159 ms	`call:`

v15 numbers forthcoming — benchmarks live in the Brinq internal repo.

Training

Base: unsloth/functiongemma-270m-it (BF16)
Method: LoRA fine-tune via Unsloth + TRL (SFTTrainer)
Hardware: A100 80GB (Docker, unsloth image)
Quantization: llama.cpp convert_hf_to_gguf.py --outtype f16 then llama-quantize ... 15 (Q4_K_M)

Training scripts, curated datasets, and eval harnesses live in Brinq's internal repo (not public). For the related Coral demo's dataset generators and fine-tune recipe (which are shipping public), see BrinqAI/coral-functiongemma-demo (currently private, planned public around Google IO 2026).

License

Gemma Terms of Use. By using this model you agree to the terms at https://ai.google.dev/gemma/terms.

Citation

@misc{brinqai_smartpanel_functiongemma_2026,
  author       = {Brinq AI},
  title        = {SmartPanel FunctionGemma 270M},
  year         = 2026,
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/BrinqAI/smartpanel-functiongemma-270m}},
}

Acknowledgements

Google DeepMind for FunctionGemma 270M
Unsloth for the fast fine-tune path
Synaptics Astra team for the SL2619 / Astra SDK

Downloads last month: 140

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

4-bit

16-bit

Model tree for BrinqAI/smartpanel-functiongemma-270m

Base model

google/functiongemma-270m-it

Finetuned

unsloth/functiongemma-270m-it

Quantized

(8)

this model