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

Libraries

How to use batiai/gemma-4-E4B-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="batiai/gemma-4-E4B-it-GGUF",
	filename="google-gemma-4-E4B-it-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use batiai/gemma-4-E4B-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf batiai/gemma-4-E4B-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf batiai/gemma-4-E4B-it-GGUF:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/batiai/gemma-4-E4B-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use batiai/gemma-4-E4B-it-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/batiai/gemma-4-E4B-it-GGUF:Q4_K_M

Ollama
How to use batiai/gemma-4-E4B-it-GGUF with Ollama:
```
ollama run hf.co/batiai/gemma-4-E4B-it-GGUF:Q4_K_M
```

Unsloth Studio

How to use batiai/gemma-4-E4B-it-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 batiai/gemma-4-E4B-it-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 batiai/gemma-4-E4B-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for batiai/gemma-4-E4B-it-GGUF to start chatting

How to use batiai/gemma-4-E4B-it-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use batiai/gemma-4-E4B-it-GGUF with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

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

Lemonade

How to use batiai/gemma-4-E4B-it-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Gemma 4 E4B-it GGUF — Quantized by BatiAI

Optimized GGUF quantizations of google/gemma-4-E4B-it — the larger Edge variant of Gemma 4 with full multimodal support (text + image + audio). Built directly from official Google BF16 weights by BatiAI for BatiFlow.

E4B doubles the parameters of E2B while keeping audio support. Best small-Mac choice when you want voice + image + text but need more reasoning headroom than E2B.

Quick Start

# Recommended
ollama pull batiai/gemma4-e4b:q4

# Higher quality
ollama pull batiai/gemma4-e4b:q6

Available Quantizations

Tag	Quant	Size	Recommended For
`:q4`	Q4_K_M	~2.8 GB	balanced (recommended default)
`:q6`	Q6_K	~3.6 GB	higher quality, near-lossless

Two modes — text-only by default, multimodal opt-in

Upstream Gemma 4 E4B-it is fully multimodal — text + image + audio in one model. In the GGUF ecosystem this is delivered as two files: a main model.gguf (text tower) and a separate mmproj.gguf that holds both vision and audio encoders together (a single 1411-tensor projector covering image and speech input).

	Text-only (default)	Multimodal (opt-in)
Files needed	main GGUF only	main GGUF + `mmproj-BF16.gguf`
Capabilities	Q&A, coding, tool calling, agents	+ image (OCR, captioning, visual reasoning) + audio (speech understanding)
`ollama pull`	✅ single command	⚠ Ollama mmproj integration is still rough — use llama.cpp directly
Disk / RAM	smaller (no projector weights)	larger (+ ~946 MB)
Recommended for	most users (chat, code, agents)	OCR, image / speech understanding

Multimodal usage (llama.cpp)

# Pick a main model (text tower)
wget https://huggingface.co/batiai/Gemma-4-E4B-it-GGUF/resolve/main/google-gemma-4-E4B-it-Q4_K_M.gguf

# Get the multimodal projector (vision + audio in one file)
wget https://huggingface.co/batiai/Gemma-4-E4B-it-GGUF/resolve/main/mmproj-BF16.gguf

Server mode (image input via OpenAI-compatible Vision API):

llama-server \
  -m google-gemma-4-E4B-it-Q4_K_M.gguf \
  --mmproj mmproj-BF16.gguf \
  -c 32768 --host 127.0.0.1 --port 8080

curl http://127.0.0.1:8080/v1/chat/completions -d '{
  "messages": [{
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}},
      {"type": "text", "text": "What does this show?"}
    ]
  }]
}'

One-shot CLI with image / audio:

# Image
llama-mtmd-cli -m google-gemma-4-E4B-it-Q4_K_M.gguf --mmproj mmproj-BF16.gguf \
  --image ~/Desktop/photo.jpg -p "describe this image"

# Audio
llama-mtmd-cli -m google-gemma-4-E4B-it-Q4_K_M.gguf --mmproj mmproj-BF16.gguf \
  --audio ~/Downloads/voice.wav -p "transcribe and summarize"

mmproj quantization

File	Quant	Size	Why this only?
`mmproj-BF16.gguf`	BF16	~946 MB	The combined vision + audio projector tensors don't satisfy K-quant block alignment, so Q6_K aborts on this projector. BF16 is the only safe choice today — applies to every quantizer of this model. The main text GGUF is unaffected.

Why E series (E2B / E4B) vs 26B / 31B?

	E2B / E4B	26B-A4B / 31B
Audio support	✅	❌ (vision only)
Min RAM	8 GB+	24 GB+
Speed	very fast (small)	slower (larger)
Reasoning depth	lower	higher
Use case	edge / mobile-class Mac / voice + image	desktop chat + agents

If you need voice + image + text in one model on a small Mac, the E series is the only Gemma 4 option. E4B if you want a bit more capability than E2B.

Why BatiAI?

	BatiAI	Third-party (unsloth, etc.)
Source	Quantized directly from official Google weights	Often re-quantized from other GGUFs
Compatibility	✅ Verified on Ollama 0.20+	❌ Known issues with Ollama 0.20+
Tested on	Real Mac mini M4 (16 GB) + MacBook Pro M4 Max	Often untested
Tool calling	✅ Verified with BatiFlow's 57 tool functions	Often broken
Korean	✅ Validated	Not tested
Multimodal	✅ Vision + audio mmproj available	Often missing
Signing	`general.author: BatiAI` for provenance	Varies

About BatiFlow

flow.bati.ai

BatiFlow is a macOS-native AI desktop automation app — just 5 MB, built with Swift.

Free & Unlimited — On-device AI via Ollama, no API costs
100 % Private — All data stays on your Mac
Ultra Lightweight — Native macOS app, only 5 MB
57 built-in tools — calendar, notes, reminders, files, email, browser, messaging, and more

Related models in the BatiAI Gemma 4 lineup

Model	Modalities	Min RAM	Repo
Gemma 4 E2B-it	text + image + audio	8 GB	batiai/Gemma-4-E2B-it-GGUF
Gemma 4 E4B-it	text + image + audio	8 GB	this repo
Gemma 4 26B-A4B-it	text + image / video (no audio)	24 GB	batiai/Gemma-4-26B-A4B-it-GGUF
Gemma 4 31B-it	text + image / video (no audio)	24 GB	batiai/Gemma-4-31B-it-GGUF

Technical Details

Original Model: google/gemma-4-E4B-it
Architecture: Gemma 4 (Edge variant)
Modalities: Text (primary) + Image + Audio (via opt-in mmproj)
License: Gemma (commercial use permitted under terms)
Quantized with: llama.cpp
Quantized by: BatiAI
GGUF metadata: general.author: BatiAI, general.url: https://flow.bati.ai

License

Mirrors the upstream Gemma license. Commercial use permitted per Google's Gemma terms.

BatiAI's quantization pipeline is provided under MIT.

Downloads last month: 924

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

6-bit

Model tree for batiai/gemma-4-E4B-it-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(224)

this model

Collection including batiai/gemma-4-E4B-it-GGUF

🍎 Gemma 4 — Google's Latest

Collection

Gemma 4 quantizations from Google's official weights. Best entry for 16GB Mac mini M4 (E4B Q4 = 57 t/s). • 4 items • Updated Apr 25