Instructions to use helenk/gemma-4-E4B-finetune-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 helenk/gemma-4-E4B-finetune-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 helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf helenk/gemma-4-E4B-finetune-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 helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf helenk/gemma-4-E4B-finetune-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 helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf helenk/gemma-4-E4B-finetune-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 helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M

Use Docker

docker model run hf.co/helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use helenk/gemma-4-E4B-finetune-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "helenk/gemma-4-E4B-finetune-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": "helenk/gemma-4-E4B-finetune-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M

Ollama
How to use helenk/gemma-4-E4B-finetune-GGUF with Ollama:
```
ollama run hf.co/helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use helenk/gemma-4-E4B-finetune-GGUF with Docker Model Runner:
```
docker model run hf.co/helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M
```

Lemonade

How to use helenk/gemma-4-E4B-finetune-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull helenk/gemma-4-E4B-finetune-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-finetune-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

helenk commited on May 9

Commit

41a7b77

verified ·

1 Parent(s): d5b2fd3

Upload E4B Q4_K_M GGUF (2026-05-09 retrain) — llama.cpp convert_hf_to_gguf.py + llama-quantize Q4_K_M from peft-merged fp16 safetensors. 5.0 GB; loads in Ollama via Modelfile (FROM gemma-4-E4B-offlineaid-Q4_K_M.gguf, RENDERER gemma4). Tier A held-out: format-OK 70.3% with RAG (vs stock+RAG 53.2%); AR format 21.6%->54.1% (2.5x).

Browse files

Files changed (1) hide show

gemma-4-E4B-offlineaid-Q4_K_M.gguf +2 -2

gemma-4-E4B-offlineaid-Q4_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e14f6c39eed42a9c1c12a137c45455d47e41bdafaaa8a2cc94e716e0e4d935
-size 5302271712

 version https://git-lfs.github.com/spec/v1
+oid sha256:5816bb6a011a1e7bdf8404ba1a07673b72296cddaaa114be147c95225718ac5f
+size 5302257888