Instructions to use dahus/gemma-4-e2b-Q6_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dahus/gemma-4-e2b-Q6_K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dahus/gemma-4-e2b-Q6_K-GGUF",
	filename="gemma-4-e2b-Q6_K.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 dahus/gemma-4-e2b-Q6_K-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 dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

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 dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

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 dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

Use Docker

docker model run hf.co/dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use dahus/gemma-4-e2b-Q6_K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dahus/gemma-4-e2b-Q6_K-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": "dahus/gemma-4-e2b-Q6_K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

Ollama
How to use dahus/gemma-4-e2b-Q6_K-GGUF with Ollama:
```
ollama run hf.co/dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K
```

Unsloth Studio

How to use dahus/gemma-4-e2b-Q6_K-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 dahus/gemma-4-e2b-Q6_K-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 dahus/gemma-4-e2b-Q6_K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dahus/gemma-4-e2b-Q6_K-GGUF to start chatting

How to use dahus/gemma-4-e2b-Q6_K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

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": "dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dahus/gemma-4-e2b-Q6_K-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 dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

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 dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use dahus/gemma-4-e2b-Q6_K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

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 "dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K" \
  --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"

Docker Model Runner
How to use dahus/gemma-4-e2b-Q6_K-GGUF with Docker Model Runner:
```
docker model run hf.co/dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K
```

Lemonade

How to use dahus/gemma-4-e2b-Q6_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dahus/gemma-4-e2b-Q6_K-GGUF:Q6_K

Run and chat with the model

lemonade run user.gemma-4-e2b-Q6_K-GGUF-Q6_K

List all available models

lemonade list

Gemma 4 E2B — Q6_K GGUF

6-bit quantized GGUF version of google/gemma-4-e2b-it.
Near-lossless quantization — 94% Top-1 agreement with F16 at a fraction of the size.

Other quantizations in this series:
Q2_K · Q3_K_S · Q3_K_M · Q4_K_S · Q4_K_M · Q5_K_S · Q5_K_M · Q8

File Info

Property	Value
Format	GGUF Q6_K
File size	3.58 GB
Bits per weight	~6
Size vs F16	2.4× smaller

Benchmark Results

Tested across 4 categories (Math, Logic, Code, Science), 3 prompts each.
Greedy decoding, 200 max new tokens. Metrics compare logit distributions vs F16 baseline.

Results by Category

Category	Speed (tok/s)	SQNR	Top-1 Agreement	KL Divergence
🔢 Math	19.7	28.7 dB	94.3%	0.0796
🧠 Logic	19.9	29.3 dB	93.2%	0.0891
💻 Code	20.0	29.0 dB	93.6%	0.0502
🔬 Science	19.9	27.8 dB	95.1%	0.0784
Overall	19.9	28.72 dB	94.1%	0.0743

Quantization Comparison

Model	Size	Speed (tok/s)	vs F16 speed	SQNR	Top-1 Agree	KL Div
F16 (baseline)	8.67 GB	5.7	1.0×	baseline	baseline	baseline
Q4_K_M	3.19 GB	24.0	4.2×	20.33 dB	82.4%	0.3356
Q5_K_M	3.38 GB	22.0	3.9×	23.25 dB	86.9%	0.1248
Q6_K (this)	3.58 GB	19.9	3.5×	28.72 dB	94.1%	0.0743
Q8	4.63 GB	16.2	2.9×	37.11 dB	96.0%	0.0171

Key Findings

Quality: 94.1% Top-1 agreement — crosses the "near-identical to F16" threshold; only Q8 is better
SQNR: 28.72 dB — a substantial 5.5 dB jump over Q5_K_M; outputs are essentially indistinguishable from F16 in practice
Speed: 19.9 tok/s — 3.5× faster than F16
Size: 3.58 GB — only 1 GB more than Q4_K_M for a major quality improvement
vs Q8: Q6_K is 1.05 GB smaller and 3.7 tok/s faster, with only a small quality difference (94.1 vs 96.0% Top-1)
Best for: Quality-sensitive tasks where you want near-F16 fidelity but still need to fit under ~5 GB; scientific explanation, precise reasoning, complex multi-step code

Usage

# llama.cpp CLI
./llama-cli -m gemma-4-e2b-q6k.gguf -p "Explain the difference between supervised and reinforcement learning." -n 200

# llama-cpp-python
from llama_cpp import Llama

llm = Llama(model_path="gemma-4-e2b-q6k.gguf", n_ctx=2048)
output = llm("Explain the difference between supervised and reinforcement learning.", max_tokens=200)
print(output["choices"][0]["text"])

Hardware

Tested on: CPU inference (llama.cpp)
Context: 2048 tokens | Greedy decoding

Downloads last month: 49

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

6-bit