Kenntkim66/snowclaw-gemma4-e2b-ft-gguf

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

Files

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

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

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)