Instructions to use nikitayev/gemma-4-E4B-it-1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikitayev/gemma-4-E4B-it-1M with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="nikitayev/gemma-4-E4B-it-1M")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("nikitayev/gemma-4-E4B-it-1M")
model = AutoModelForImageTextToText.from_pretrained("nikitayev/gemma-4-E4B-it-1M")

llama-cpp-python

How to use nikitayev/gemma-4-E4B-it-1M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nikitayev/gemma-4-E4B-it-1M",
	filename="google_gemma-4-E4B-it-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use nikitayev/gemma-4-E4B-it-1M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nikitayev/gemma-4-E4B-it-1M:Q8_0
# Run inference directly in the terminal:
llama-cli -hf nikitayev/gemma-4-E4B-it-1M:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nikitayev/gemma-4-E4B-it-1M:Q8_0
# Run inference directly in the terminal:
llama-cli -hf nikitayev/gemma-4-E4B-it-1M:Q8_0

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 nikitayev/gemma-4-E4B-it-1M:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf nikitayev/gemma-4-E4B-it-1M:Q8_0

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 nikitayev/gemma-4-E4B-it-1M:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nikitayev/gemma-4-E4B-it-1M:Q8_0

Use Docker

docker model run hf.co/nikitayev/gemma-4-E4B-it-1M:Q8_0

LM Studio
Jan

vLLM

How to use nikitayev/gemma-4-E4B-it-1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nikitayev/gemma-4-E4B-it-1M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikitayev/gemma-4-E4B-it-1M",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/nikitayev/gemma-4-E4B-it-1M:Q8_0

SGLang

How to use nikitayev/gemma-4-E4B-it-1M with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nikitayev/gemma-4-E4B-it-1M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikitayev/gemma-4-E4B-it-1M",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nikitayev/gemma-4-E4B-it-1M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikitayev/gemma-4-E4B-it-1M",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use nikitayev/gemma-4-E4B-it-1M with Ollama:
```
ollama run hf.co/nikitayev/gemma-4-E4B-it-1M:Q8_0
```

Unsloth Studio new

How to use nikitayev/gemma-4-E4B-it-1M 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 nikitayev/gemma-4-E4B-it-1M 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 nikitayev/gemma-4-E4B-it-1M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nikitayev/gemma-4-E4B-it-1M to start chatting

Pi new

How to use nikitayev/gemma-4-E4B-it-1M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf nikitayev/gemma-4-E4B-it-1M:Q8_0

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": "nikitayev/gemma-4-E4B-it-1M:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nikitayev/gemma-4-E4B-it-1M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf nikitayev/gemma-4-E4B-it-1M:Q8_0

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 nikitayev/gemma-4-E4B-it-1M:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use nikitayev/gemma-4-E4B-it-1M with Docker Model Runner:
```
docker model run hf.co/nikitayev/gemma-4-E4B-it-1M:Q8_0
```

Lemonade

How to use nikitayev/gemma-4-E4B-it-1M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nikitayev/gemma-4-E4B-it-1M:Q8_0

Run and chat with the model

lemonade run user.gemma-4-E4B-it-1M-Q8_0

List all available models

lemonade list

Hugging Face | GitHub | Launch Blog | Documentation
License: Apache 2.0 | Authors: Google DeepMind

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: E2B, E4B, 26B A4B, and 31B. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.

Gemma 4 introduces key capability and architectural advancements:

Reasoning – All models in the family are designed as highly capable reasoners, with configurable thinking modes.
Extended Multimodalities – Processes Text, Image with variable aspect ratio and resolution support (all models), Video, and Audio (featured natively on the E2B and E4B models).
Diverse & Efficient Architectures – Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment.
Optimized for On-Device – Smaller models are specifically designed for efficient local execution on laptops and mobile devices.
Increased Context Window – The small models feature a 128K context window, while the medium models support 256K.
Enhanced Coding & Agentic Capabilities – Achieves notable improvements in coding benchmarks alongside native function-calling support, powering highly capable autonomous agents.
Native System Prompt Support – Gemma 4 introduces native support for the system role, enabling more structured and controllable conversations.

# Gemma-4-E4B-it LongRoPE 1M GGUF Q8_0

**Model with extended context window, based on `google/gemma-4-E4B-it` using the LongRoPE method.**

- 🧠 **Base model:** [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it)  
- 📏 **Original context:** 128K tokens  
- 🚀 **Extended context:** 1,048,576 tokens (1M) via **LongRoPE**  
- 📦 **Format:** GGUF, quantization **Q8_0**  
- ⚙️ **Compatibility:** LM Studio, llama.cpp, and other GGUF‑compatible engines

---

## 🔍 Description

This version of the model was obtained by converting the official instruction-tuned `google/gemma-4-E4B-it` into the universal GGUF format and then extending the context window using the **LongRoPE** technique.  
The original context length was 128 thousand tokens; after applying LongRoPE, the model can handle up to **1 million tokens** of continuous dialogue.  
Quantization is performed in 8-bit `Q8_0` format, offering a good balance between quality and performance.

> ⚠️ **Important:** Extending the context by interpolating positional embeddings inevitably affects quality. The model has become somewhat “dumber” compared to the original, especially on complex multi-step reasoning tasks. However, with a proper set of parameters and Flash Attention disabled, it delivers satisfactory results on standard tasks.

---

## 📊 Performance

Test system:

| Component | Specification |
|-----------|---------------|
| CPU | 2× Intel Xeon E5-2695 v4 @ 2.10GHz (AVX, AVX2) |
| RAM | 512 GB |
| GPU | NVIDIA GeForce RTX 3060 12 GB (CUDA 12.9, Compute Capability 8.6) |

**Inference speed:**

- **LM Studio 0.4.12 (Build 1)**: stable **~21 tokens/s**  
- **llama.cpp (server, no CPU offload)**:  
  - Start: **34 tokens/s**  
  - End of context fill: drops to **18 tokens/s**

---

## 🧩 Recommended settings

### For LM Studio

Create a preset named, e.g., “BEST”, and set the following parameters:

```json
{
  "identifier": "@local:best",
  "name": "BEST",
  "changed": true,
  "operation": {
    "fields": [
      { "key": "llm.prediction.temperature", "value": 1.3 },
      { "key": "llm.prediction.contextOverflowPolicy", "value": "rollingWindow" },
      { "key": "llm.prediction.llama.cpuThreads", "value": 32 },
      { "key": "llm.prediction.topKSampling", "value": 500 },
      { "key": "llm.prediction.repeatPenalty", "value": { "checked": true, "value": 1 } },
      { "key": "llm.prediction.llama.presencePenalty", "value": { "checked": true, "value": 0 } },
      { "key": "llm.prediction.topPSampling", "value": { "checked": true, "value": 0.99 } },
      { "key": "llm.prediction.minPSampling", "value": { "checked": true, "value": 0.05 } }
    ]
  },
  "load": {
    "fields": []
  }
}

Temperature is recommended in the range 1.0 – 1.3.
Keep Flash Attention disabled — with it, the model degrades more.

For llama.cpp (server)

Example launch, under which the model reliably solves logical “Einstein puzzles”:

"E:\LLM\llama.cpp\build\bin\llama-server.exe" \
  -m "C:/LLM/Nikitayev/google_gemma-4-E4B-it/google_gemma-4-E4B-it-q8_0.gguf" \
  --mmproj "C:/LLM/lmstudio-community/gemma-4-E4B-it-GGUF/mmproj-gemma-4-E4B-it-BF16.gguf" \
  --host 127.0.0.1 --port 8080 \
  --timeout 60000 --threads-http -1 \
  --ctx-size 1048576 \
  --flash-attn on --fit off --kv-offload \
  --mmap --cont-batching --webui --jinja --embedding --metrics --slots --cache-prompt --mlock \
  --reasoning-format auto \
  --temp 0.75 --dynatemp-range 0.75 \
  --top-k 10000 --top-p 0.99 --min-p 0.05 \
  --xtc-probability 0 \
  --repeat-penalty 1.0 --presence-penalty 0.0 --frequency-penalty 0.0 \
  --dry-multiplier 0.0 \
  --samplers "penalties;dry;top_n_sigma;top_k;typ_p;top_p;min_p;xtc;temperature" \
  --n-predict 8192 --seed 0

Note: The --flash-attn on flag is left here because in some llama.cpp scenarios the combination of flash attention + sampling parameters works better than in LM Studio. Try --flash-attn off if you experience instability.

🧪 Observations and Conclusions

Extending the context with LongRoPE leads to a noticeable but not critical drop in the model’s “intelligence”.
With Flash Attention disabled, the quality of answers on standard conversational tasks remains acceptable.
On complex logical tasks, the model remains capable with carefully chosen sampling parameters (see examples above).
Using GPU offloading is critical; CPU-only inference drops speed dramatically. The RTX 3060 with 12 GB allows loading all model weights into VRAM.

📁 Files

google_gemma-4-E4B-it-q8_0.gguf – main GGUF Q8_0 model with extended context.
mmproj-gemma-4-E4B-it-BF16.gguf – multimodal embedding projector (original, BF16), required for the full pipeline.