Instructions to use daniloreddy/gemma-4-E2B-it_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use daniloreddy/gemma-4-E2B-it_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 daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf daniloreddy/gemma-4-E2B-it_GGUF: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 daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf daniloreddy/gemma-4-E2B-it_GGUF: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 daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

Use Docker

docker model run hf.co/daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use daniloreddy/gemma-4-E2B-it_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "daniloreddy/gemma-4-E2B-it_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": "daniloreddy/gemma-4-E2B-it_GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

Ollama
How to use daniloreddy/gemma-4-E2B-it_GGUF with Ollama:
```
ollama run hf.co/daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M
```
Unsloth Desktop

How to use daniloreddy/gemma-4-E2B-it_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use daniloreddy/gemma-4-E2B-it_GGUF with Docker Model Runner:
```
docker model run hf.co/daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M
```

Lemonade

How to use daniloreddy/gemma-4-E2B-it_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E2B-it_GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use daniloreddy/gemma-4-E2B-it_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 daniloreddy/gemma-4-E2B-it_GGUF: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 daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use daniloreddy/gemma-4-E2B-it_GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M

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 "daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M" \
  --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"

daniloreddy commited on Apr 5

Commit

bd681e4

verified ·

1 Parent(s): c5460d6

Update README.md

Browse files

Files changed (1) hide show

README.md +61 -3

README.md CHANGED Viewed

@@ -1,3 +1,61 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+base_model: google/gemma-4-E2B-it
+tags:
+- llama.cpp
+- gguf
+- quantized
+- text-generation
+- lightweight
+- lmstudio
+- jan
+- cobalt
+- text-generation-webui
+---
+# Gemma-4-E2B-IT - GGUF High-Quality Quantizations
+This repository provides **GGUF** quantized versions of the [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) model, optimized for local execution using `llama.cpp` and compatible ecosystems.
+## 📌 Version Notes
+All quantizations were generated from the official **FP16** weights.
+- **Target:** Efficient execution on consumer hardware, mobile/edge devices, and systems with limited memory.
+- **Performance:** The output quality (reasoning, coherence, and accuracy) is strictly dependent on the base model's parameter scale (1B).
+## 📊 Quantization Table
+| File | Method | Bit | Description |
+| :--- | :--- | :--- | :--- |
+| **fp16.gguf** | FP16 | 16-bit | **Original Weights.** No quantization applied. Maximum fidelity. |
+| **Q8_0.gguf** | Q8_0 | 8-bit | **Near-lossless.** Practically identical to the original model with lower memory footprint. |
+| **Q5_K_M.gguf** | Q5_K_M | 5-bit | **High Precision.** Minimizes quantization error for critical tasks. |
+| **Q4_K_M.gguf** | Q4_K_M | 4-bit | **Recommended.** Best balance between speed and performance. |
+| **Q4_K_S.gguf** | Q4_K_S | 4-bit | **Fast/Small.** Optimized for maximum throughput and low RAM usage. |
+## 🛠️ Technical Details
+- **Quantization Date:** 2026-04-05
+- **Tool used:** `llama-quantize` (llama.cpp)
+- **Method:** K-Quantization (optimized for AVX2/AVX-512 and modern GPU architectures).
+## 🚀 How to Use
+# Start a local OpenAI-compatible server with a web UI:
+### llama.cpp (CLI) using model from HuggingFace
+```bash
+./llama-cli -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M -p "User: Hello! Assistant:" -n 512 --temp 0.7
+```
+### llama.cpp (CLI) using downloaded model
+```bash
+./llama-cli -m path/to/gemma-4-E2B-it_Q4_K_M.gguf -p "User: Hello! Assistant:" -n 512 --temp 0.7
+```
+### llama.cpp (SERVER) using model from HuggingFace
+```bash
+./llama-server -hf daniloreddy/gemma-4-E2B-it_GGUF:Q4_K_M --port 8080 -c 4096
+```
+### llama.cpp (SERVER) using downloaded model
+```bash
+./llama-server -m /path/to/gemma-4-E2B-it_Q4_K_M.gguf --port 8080 -c 4096
+```