Instructions to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M 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 sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M: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 sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M: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 sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M

LM Studio
Jan

vLLM

How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunil-pathak/gemma-4-E4B-it-Q4_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunil-pathak/gemma-4-E4B-it-Q4_K_M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M

Ollama
How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with Ollama:
```
ollama run hf.co/sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M
```
Unsloth Desktop

How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M: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": "sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M
```

Lemonade

How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-it-Q4_K_M-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M: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 sunil-pathak/gemma-4-E4B-it-Q4_K_M:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sunil-pathak/gemma-4-E4B-it-Q4_K_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sunil-pathak/gemma-4-E4B-it-Q4_K_M: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 "sunil-pathak/gemma-4-E4B-it-Q4_K_M: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"

sunil-pathak commited on Apr 19

Commit

2152c7a

verified ·

1 Parent(s): 0458b01

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -16,9 +16,11 @@ pipeline_tag: text-generation
 ## 📊 Performance Metrics
 - **Size:** 4.97 GB
-- **Speed:** 2.68 tokens/sec
-- **Format:** GGUF (llama.cpp optimized)
 - **Quantization:** Q4_K_M
 ---
@@ -30,7 +32,7 @@ This repository contains a **GGUF quantized version** of:
 - **Base Model:** gemma-4-E4B-it
 - **Format:** GGUF (optimized for llama.cpp inference)
 - **Precision:** Q4_K_M
-- **Purpose:** Efficient local inference on CPU/GPU
 GGUF format provides:
 - Fast loading via memory mapping
@@ -56,7 +58,9 @@ GGUF format provides:
 | Format | GGUF |
 | Precision | Q4_K_M |
 | Runtime | llama.cpp |
-| Use Case | Local inference / deployment |
 ---

 ## 📊 Performance Metrics
+- **Hardware:** Intel(R) Xeon(R) CPU @ 2.20GHz (4 vCPUs)
 - **Size:** 4.97 GB
+- **Speed (Generation):** 4.18 tokens/sec
+- **Speed (Prompt):** 9.83 tokens/sec
+- **KV Cache Usage:** 0.0143 GB
 - **Quantization:** Q4_K_M
 ---
 - **Base Model:** gemma-4-E4B-it
 - **Format:** GGUF (optimized for llama.cpp inference)
 - **Precision:** Q4_K_M
+- **Efficiency Score:** 0.8412 (TPS/GB)
 GGUF format provides:
 - Fast loading via memory mapping
 | Format | GGUF |
 | Precision | Q4_K_M |
 | Runtime | llama.cpp |
+| Benchmark Hardware | Intel(R) Xeon(R) CPU @ 2.20GHz (4 vCPUs) |
+| Context Latency | 52.44s |
+| Memory (KV) | 0.0143 GB |
 ---