Instructions to use KillerBoss/functiongemma-plantgame-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KillerBoss/functiongemma-plantgame-de with LiteRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KillerBoss/functiongemma-plantgame-de 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 KillerBoss/functiongemma-plantgame-de:F16
# Run inference directly in the terminal:
llama cli -hf KillerBoss/functiongemma-plantgame-de:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KillerBoss/functiongemma-plantgame-de:F16
# Run inference directly in the terminal:
llama cli -hf KillerBoss/functiongemma-plantgame-de:F16

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 KillerBoss/functiongemma-plantgame-de:F16
# Run inference directly in the terminal:
./llama-cli -hf KillerBoss/functiongemma-plantgame-de:F16

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 KillerBoss/functiongemma-plantgame-de:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KillerBoss/functiongemma-plantgame-de:F16

Use Docker

docker model run hf.co/KillerBoss/functiongemma-plantgame-de:F16

LM Studio
Jan
Ollama
How to use KillerBoss/functiongemma-plantgame-de with Ollama:
```
ollama run hf.co/KillerBoss/functiongemma-plantgame-de:F16
```
Unsloth Desktop
Docker Model Runner
How to use KillerBoss/functiongemma-plantgame-de with Docker Model Runner:
```
docker model run hf.co/KillerBoss/functiongemma-plantgame-de:F16
```

Lemonade

How to use KillerBoss/functiongemma-plantgame-de with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KillerBoss/functiongemma-plantgame-de:F16

Run and chat with the model

lemonade run user.functiongemma-plantgame-de-F16

List all available models

lemonade list

Atomic Chat

FunctionGemma PlantGame DE — On-Device-Artefakte (LiteRT / TFLite / NPU)

Dieses Repo enthält das für Google AI Edge Gallery aufbereitete Fine-Tune functiongemma-plantgame-de (Basis: google/functiongemma-270m-it, Architektur: Gemma 3 270M) für die lokale Ausführung auf Android (z. B. Samsung Galaxy S26 Ultra, Snapdragon 8 Elite Gen 5 / SM8850).

Artefakte (Ordner `litertlm/`)

Datei	Format	Ziel-Hardware	Quantisierung	Kontext
`functiongemma-plantgame-de-wi8emb4-ekv1280.litertlm`	LiteRT-LM (`.litertlm`)	CPU + GPU	8-bit Gewichte, 4-bit Embeddings (per-channel)	Prefill-Chunks 128, KV-Cache 1280
`functiongemma-plantgame-de-int8-ekv1280.task`	MediaPipe Task (`.task`)	CPU + GPU	8-bit dynamisch + 4-bit Embeddings	Prefill-Chunks 128, KV-Cache 1280
`functiongemma-plantgame-de-qnn-sm8850.litertlm`	LiteRT-LM, QNN-AOT-kompiliert	NPU (Hexagon) — nur Snapdragon SM8850	w8a16 (a16w8) via LiteRT NPU-Compiler	Prefill-Chunks 128, KV-Cache 1280

Verwendung in Google AI Edge Gallery

AI Edge Gallery installieren (Standard-APK für CPU/GPU; NPU-Preview-APK für Snapdragon-NPU).
In der App: Add model → URL auf die .litertlm- bzw. .task-Datei in diesem Repo eingeben (oder Datei über den Dateimanager importieren).
CPU/GPU-Artefakt: normal starten; in den Einstellungen lässt sich GPU-Beschleunigung aktivieren.
NPU-Artefakt: nur in der NPU-fähigen Gallery-Build auf einem Gerät mit Snapdragon SM8850 (Galaxy S26 Ultra) starten — die QNN-Kompilierung ist SoC-spezifisch und läuft auf anderen Chips nicht.

Technik

Konvertierung: litert-torch export_hf (LiteRT-Torch Generative Pipeline)
NPU: compile_litertlm mit Backend qualcomm, SoC SM8850, O3-Optimierung
Signatur-Konventionen: prefill_128, Decode mit transponiertem KV-Cache
Tokenizer: SentencePiece (tokenizer.model), Start-Token <bos>, Stop-Token <eos> / <end_of_turn>

Trainingsquelle

Fein-Tuning auf Kaggle (LoRA-frei, Full-FT, 2 Epochen, 3825 Trainings-/675 Eval-Samples): Exact-Match 148/150 = 98,7 % auf dem deutschen PlantGame-Function-Calling-Eval.

Downloads last month: -

Safetensors

Model size

0.3B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

FunctionGemma PlantGame DE — On-Device-Artefakte (LiteRT / TFLite / NPU)

Artefakte (Ordner litertlm/)

Verwendung in Google AI Edge Gallery

Technik

Trainingsquelle

Artefakte (Ordner `litertlm/`)