---

license: gemma

license_link: https://ai.google.dev/gemma/terms

pipeline_tag: text-generation

tags:

• gemma
• gemma-4
• gguf
• ollama
• conversational

base_model: google/gemma-4-E2B-it

---

Google Gemma-4-E2B-IT - GGUF (Q4_K_M)

This repository contains the quantized Q4_K_M GGUF weights for google/gemma-4-E2B-it, configured for 1-click execution in Ollama and llama.cpp.

---

⚡ Direct Ollama Run (1-Line Command)

Run this model instantly in Ollama without manual downloads:

ollama run hf.co/jamesatron1512/gemma-4-E2B-it-GGUF

Or specify the exact quantization tag:

ollama run hf.co/jamesatron1512/gemma-4-E2B-it-GGUF:Q4_K_M

---

🚀 Model Details

• Architecture: Gemma-4 (2B Parameters, 262k Vocabulary)
• Precision: Q4_K_M (Quantized 4-bit)
• Disk Size: ~2.96 GB
• Context Length: Up to 8,192 tokens
• Chat Format: Gemma Turn Format (<start_of_turn>user ... <end_of_turn><start_of_turn>model)
• System Prompt: Supported via template, default is left clean to prevent fixation.

---

💻 Python API Usage via Ollama

import requests

response = requests.post(
    "http://localhost:11434/api/generate",
    json={
        "model": "hf.co/jamesatron1512/gemma-4-E2B-it-GGUF",
        "prompt": "Explain the concept of neural network loss functions in simple terms.",
        "stream": False,
        "options": {
            "temperature": 0.7,
            "top_p": 0.9,
            "num_predict": 128
        }
    }
)

print(response.json()["response"])