Instructions to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Kenntkim66/snowclaw-gemma4-e2b-ft-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Kenntkim66/snowclaw-gemma4-e2b-ft-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf 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 Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

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 Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

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 Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

Use Docker

docker model run hf.co/Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

LM Studio
Jan

vLLM

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kenntkim66/snowclaw-gemma4-e2b-ft-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": "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

SGLang

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with Ollama:
```
ollama run hf.co/Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16
```

Unsloth Studio

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-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 Kenntkim66/snowclaw-gemma4-e2b-ft-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 Kenntkim66/snowclaw-gemma4-e2b-ft-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kenntkim66/snowclaw-gemma4-e2b-ft-gguf to start chatting

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

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": "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

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 Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

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 "Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16" \
  --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 Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with Docker Model Runner:
```
docker model run hf.co/Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16
```

Lemonade

How to use Kenntkim66/snowclaw-gemma4-e2b-ft-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kenntkim66/snowclaw-gemma4-e2b-ft-gguf:BF16

Run and chat with the model

lemonade run user.snowclaw-gemma4-e2b-ft-gguf-BF16

List all available models

lemonade list

SnowClaw — Fine-tuned Gemma 4 E2B for Privacy-First Tool Use

A fine-tuned Gemma 4 E2B model optimized for on-device AI tool use in the SnowClaw desktop agent. Achieves 100% tool use accuracy (7/7) on our evaluation set.

Model Details

Property	Value
Base Model	`google/gemma-4-E2B-it` (Gemma 4 E2B Instruct)
Method	LoRA (rank=64, alpha=64) via Unsloth
Training Data	2,000 synthetic tool-use examples
Epochs	15
Final Loss	0.040
Hardware	NVIDIA RTX 3090 (24GB VRAM)
Quantization	Q4_K_M (GGUF)
Vision	Multimodal — includes mmproj for image understanding

Files

File	Size	Description
`gemma-4-e2b-it.Q4_K_M.gguf`	3.2 GB	Main model (Q4_K_M quantized)
`gemma-4-e2b-it.BF16-mmproj.gguf`	942 MB	Vision projector (multimodal image encoder)
`Modelfile`	205 B	Ollama registration file

Intended Use

SnowClaw is a privacy-first desktop AI agent that runs entirely on-device. This model is fine-tuned for:

Tool Use: Executing system commands, browsing files, managing contacts/calendar
Code Generation: Writing and executing Python/AppleScript in a sandboxed environment
Screenshot Analysis: Understanding screen content via vision capabilities
Privacy: All processing stays local — zero data leaves the device

How to Use

With Ollama

# Download the GGUF files, then register with Ollama:
ollama create snowclaw -f Modelfile

# Run
ollama run snowclaw

With llama.cpp

# Text only
./llama-cli -m gemma-4-e2b-it.Q4_K_M.gguf -p "List files in my Downloads folder"

# With vision (multimodal)
./llama-mtmd-cli \
  -m gemma-4-e2b-it.Q4_K_M.gguf \
  --mmproj gemma-4-e2b-it.BF16-mmproj.gguf

Training Details

LoRA Configuration

{
  "r": 64,
  "lora_alpha": 64,
  "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
  "lora_dropout": 0,
  "task_type": "CAUSAL_LM"
}

Training Curve

Step	Loss
10	8.147
20	1.074
30	0.469
100	0.099
500	0.043
1000	0.038
1875	0.040

Dataset

2,000 synthetic examples covering:

System tool invocations (file management, process control)
Contact and calendar queries
Device information retrieval
Multi-step task planning
Safety-aware refusals

Evaluation

Metric	Score
Tool Use Accuracy	7/7 (100%)
Correct Tool Selection	7/7
Parameter Extraction	7/7

Part of SnowClaw

SnowClaw is a privacy-first AI agent built for the Google Gemma Hackathon. It features:

On-device inference via bundled Ollama
Dual security modes: Paranoid (fully offline) / Smart Search (local + anonymous SearXNG)
E2E encrypted communication between desktop and mobile
Hardware-aware model selection (auto-detects CPU/GPU/RAM)

Author

Kennt Kim — Calida Lab

License

Apache 2.0 (following Gemma's license terms)

Downloads last month: 13

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for Kenntkim66/snowclaw-gemma4-e2b-ft-gguf

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Adapter

(135)

this model

Evaluation results

Tool Use (7/7)
self-reported

100.000