Instructions to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with Transformers:

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

pipe = pipeline("image-text-to-text", model="arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled")
model = AutoModelForMultimodalLM.from_pretrained("arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled",
	filename="gemma-4-E4B-it.BF16-mmproj.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 Settings

llama.cpp

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled: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 arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled: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 arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M

Use Docker

docker model run hf.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M

LM Studio
Jan

vLLM

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled",
		"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/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M

SGLang

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled 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 "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled" \
    --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": "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled",
		"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 "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled" \
        --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": "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled",
		"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 arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with Ollama:
```
ollama run hf.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M
```

Unsloth Studio

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled 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 arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled 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 arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled to start chatting

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled: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": "arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled: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 arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with Docker Model Runner:
```
docker model run hf.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M
```

Lemonade

How to use arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled-Q4_K_M

List all available models

lemonade list

Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled

Fine-tune of Gemma 4 E4B trained on Claude 4.6 Opus reasoning traces. The goal: take a compact 4B model and teach it to actually think before answering.

💡 What this is

Standard Gemma 4 E4B is already solid. This fine-tune pushes it toward a more deliberate, structured reasoning style by training on ~2.3k high-quality Chain-of-Thought samples distilled from Claude 4.6 Opus.

The model learns to plan inside <think> tags before committing to a final answer — fewer impulsive responses, more structured breakdowns.

<think>
1. What is actually being asked here?
2. What are the constraints and edge cases?
3. Step-by-step plan...
4. Verify the logic holds.
</think>

Final answer here.

🗺️ Pipeline

google/gemma-4-E4B-it
 │
 ▼
SFT + QLoRA 4-bit (Unsloth)
 │  loss masked to responses only
 ▼
Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled
 │
 ▼
exported as GGUF (Q4_K_M + Q8_0)

⚙️ Training Details

Parameter	Value
Base model	google/gemma-4-E4B-it
Framework	Unsloth
Method	SFT + QLoRA (4-bit)
Dataset	nohurry/Opus-4.6-Reasoning-3000x-filtered
Hardware	RTX 5060 Ti 16GB
LoRA rank / alpha	16 / 16
Epochs	3
Max seq length	2048
Optimizer	adamw_8bit
Learning rate	2e-4
LR scheduler	cosine
Loss masking	train_on_responses_only

📚 Dataset

Dataset	Description
nohurry/Opus-4.6-Reasoning-3000x-filtered	~2.3k filtered Claude 4.6 Opus reasoning trajectories covering math, logic, and coding

🚀 Run it

Ollama:

ollama run hf.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled

llama.cpp:

./llama-cli -hf arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled \
  --temp 1.0 --top-p 0.95 --top-k 64

✅ Good at

Multi-step math and logic problems
Code problem decomposition and debugging
Tasks where showing reasoning is more valuable than raw speed
Structured analysis of complex prompts

⚠️ Limitations

Text only — multimodal capabilities of the base model are not trained here
Small dataset — treat this as a focused reasoning fine-tune, not a general-purpose upgrade
Still an LLM — hallucinations happen, especially on factual recall outside the training domain

📜 License

Apache 2.0 + Gemma Terms of Use.

"Claude" is a trademark of Anthropic. This project is not affiliated with or endorsed by Anthropic — the name refers to the reasoning distillation data source only.

🙏 Acknowledgements

Unsloth for making this feasible on consumer hardware, and nohurry for the dataset.

📖 Citation

@misc{arsovskidev_gemma4_opus_distilled,
  title        = {Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled},
  author       = {arsovskidev},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled}}
}

Downloads last month: 4,801

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(224)

this model

Finetunes

2 models

Quantizations

3 models

arsovskidev
/

Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled