Instructions to use meghanamakkapati/Gemma-4_quantization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meghanamakkapati/Gemma-4_quantization with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="meghanamakkapati/Gemma-4_quantization",
	filename="gemma4-E4B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "\"cats.jpg\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use meghanamakkapati/Gemma-4_quantization with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M

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 meghanamakkapati/Gemma-4_quantization:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M

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 meghanamakkapati/Gemma-4_quantization:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M

Use Docker

docker model run hf.co/meghanamakkapati/Gemma-4_quantization:Q4_K_M

LM Studio
Jan
Ollama
How to use meghanamakkapati/Gemma-4_quantization with Ollama:
```
ollama run hf.co/meghanamakkapati/Gemma-4_quantization:Q4_K_M
```

Unsloth Studio new

How to use meghanamakkapati/Gemma-4_quantization 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 meghanamakkapati/Gemma-4_quantization 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 meghanamakkapati/Gemma-4_quantization to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meghanamakkapati/Gemma-4_quantization to start chatting

Pi new

How to use meghanamakkapati/Gemma-4_quantization with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M

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": "meghanamakkapati/Gemma-4_quantization:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use meghanamakkapati/Gemma-4_quantization with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf meghanamakkapati/Gemma-4_quantization:Q4_K_M

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 meghanamakkapati/Gemma-4_quantization:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use meghanamakkapati/Gemma-4_quantization with Docker Model Runner:
```
docker model run hf.co/meghanamakkapati/Gemma-4_quantization:Q4_K_M
```

Lemonade

How to use meghanamakkapati/Gemma-4_quantization with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meghanamakkapati/Gemma-4_quantization:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4_quantization-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Gemma-4-E4B-IT — GGUF Q4_K_M Quantized

Quantized version of google/gemma-4-E4B-IT submitted to the Resilient AI Challenge — Image to Text category.

Compression

Parameter	Value
Method	Post-training quantization via llama.cpp
Format	GGUF Q4_K_M (4-bit, K-quant)
Original size	16.02 GB (FP16)
Quantized size	5.34 GB
Size reduction	67%
Vision projector	0.99 GB (BF16 GGUF)
VRAM required	~6-8 GB (fits on L4 24GB)
Hardware tested	NVIDIA A100-SXM4-40GB

Converted from HuggingFace format using convert_hf_to_gguf.py then quantized to Q4_K_M using llama-quantize. The vision projector (mmproj) is extracted separately and required for multimodal image+text inference.

Files

File	Size	Description
`gemma4-E4B-Q4_K_M.gguf`	5.34 GB	Q4_K_M quantized language model
`mmproj-BF16.gguf`	0.99 GB	Vision projector (required for images)
`llama_server_config.json`	—	Server configuration

Inference — llama-server

llama-server \
    -m gemma4-E4B-Q4_K_M.gguf \
    --mmproj mmproj-BF16.gguf \
    --host 0.0.0.0 --port 8080 \
    --n-gpu-layers 99 \
    --ctx-size 8192 \
    --temp 1.0 --top-p 0.95 --top-k 64

API Usage

curl http://localhost:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemma4",
    "messages": [{"role": "user", "content": [
      {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,<b64>"}},
      {"type": "text", "text": "Describe this image."}
    ]}],
    "max_tokens": 256
  }'

Evaluation Parameters

Parameter	Value
temperature	1.0
top_p	0.95
top_k	64
max_tokens	256

Hardware

Quantized on NVIDIA A100-SXM4-40GB. Compatible with NVIDIA L4 24GB (~6-8 GB VRAM used).

License

Apache 2.0 — same as original google/gemma-4-E4B-IT.

Downloads last month: 120

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit