---
language:
  - en
pipeline_tag: text-generation
tags:
  - gguf
  - ollama
  - tool-calling
  - mcp
  - tealkit
  - qlora
base_model:
  - google/gemma-4-E2B-it
license: mit
---

> **⚠️ This model is purpose-built for the [TealKit](https://lschaffer.github.io/tealkit) agentic AI app.**
> It is optimised for MCP tool-call generation inside TealKit's server mode.

## Model Details

| | |
|---|---|
| Base model | [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) |
| Fine-tune method | QLoRA (4-bit base, 16-bit adapters, Unsloth) |
| Quantization | Q4_K_M |
| GGUF file | `model-q4_k_m.gguf` |
| Training date | 2026-05-15 |

## Quick Start (Ollama)

```bash
ollama create gemma4-tealkit -f Modelfile
ollama run gemma4-tealkit
```

## Training Pipeline

QLoRA fine-tuning in Google Colab (Unsloth + TRL), PEFT adapter fusion, llama.cpp GGUF export.
See the [TealKit training guide](https://github.com/lschaffer/mobile_ai_agent/blob/master/scripts_training/README.md).