Instructions to use B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use B4lt/gemma4-loghub-e2b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "B4lt/gemma4-loghub-e2b-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": "B4lt/gemma4-loghub-e2b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M

Ollama
How to use B4lt/gemma4-loghub-e2b-GGUF with Ollama:
```
ollama run hf.co/B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M
```

Unsloth Studio

How to use B4lt/gemma4-loghub-e2b-GGUF 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 B4lt/gemma4-loghub-e2b-GGUF 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 B4lt/gemma4-loghub-e2b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for B4lt/gemma4-loghub-e2b-GGUF to start chatting

How to use B4lt/gemma4-loghub-e2b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf B4lt/gemma4-loghub-e2b-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": "B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use B4lt/gemma4-loghub-e2b-GGUF with Docker Model Runner:
```
docker model run hf.co/B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M
```

Lemonade

How to use B4lt/gemma4-loghub-e2b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma4-loghub-e2b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-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 B4lt/gemma4-loghub-e2b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use B4lt/gemma4-loghub-e2b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf B4lt/gemma4-loghub-e2b-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 "B4lt/gemma4-loghub-e2b-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"

gemma4-loghub-e2b-GGUF

Gemma 4 E2B fine-tuned for infrastructure, Linux, Windows, networking, cloud and application log analysis.

Files

gemma4-loghub-e2b-loghub-Q4_K_M.gguf

This is the recommended release artifact:

Base family: Gemma 4 E2B
Format: GGUF v3
Quantization: Q4_K_M
Mode: text-only language model
Tensor count: 601
Size: ~3.2 GB
Chat template: embedded Gemma 4 template
SHA256: e70b4d0009db2ec9fa4a57782d57264084572bb34bf9a4d41b76eb9559a07f73

Why Text-Only

Gemma 4 E2B is a multimodal model with language, audio and vision tensors. For log analysis we only need text inference. Some llama-server based tools fail when given a unified Gemma4 GGUF that contains the extra audio/vision tensors. This release keeps the fine-tuned language tensors and removes audio, vision and multimodal projector tensors.

llama.cpp

Use a recent llama.cpp build with Gemma4 support.

llama-server \
  -m gemma4-loghub-e2b-loghub-Q4_K_M.gguf \
  -c 4096 \
  --reasoning off

If your llama-server does not support --reasoning off, use:

llama-server \
  -m gemma4-loghub-e2b-loghub-Q4_K_M.gguf \
  -c 4096 \
  --chat-template-kwargs '{"enable_thinking":false}'

Ollama

From this directory:

ollama create gemma4-loghub-e2b:q4 -f Modelfile
ollama run gemma4-loghub-e2b:q4

Unsloth Studio

Import the real .gguf file directly:

gemma4-loghub-e2b-loghub-Q4_K_M.gguf

Do not import a symlink, the old LoRA adapter GGUF, or the unified multimodal GGUF.

Start with context length 2048 or 4096 on laptops.

Downloads last month: 33

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for B4lt/gemma4-loghub-e2b-GGUF

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

unsloth/gemma-4-E2B-it-GGUF

Quantized

(3)

this model