Instructions to use arabellako22/gifted_maths_gemma_4_gguf_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arabellako22/gifted_maths_gemma_4_gguf_v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="arabellako22/gifted_maths_gemma_4_gguf_v2",
	filename="gifted-maths-gemma-4-v2.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use arabellako22/gifted_maths_gemma_4_gguf_v2 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 arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf arabellako22/gifted_maths_gemma_4_gguf_v2: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 arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf arabellako22/gifted_maths_gemma_4_gguf_v2: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 arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M

Use Docker

docker model run hf.co/arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M

LM Studio
Jan
Ollama
How to use arabellako22/gifted_maths_gemma_4_gguf_v2 with Ollama:
```
ollama run hf.co/arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M
```

Unsloth Studio

How to use arabellako22/gifted_maths_gemma_4_gguf_v2 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 arabellako22/gifted_maths_gemma_4_gguf_v2 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 arabellako22/gifted_maths_gemma_4_gguf_v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arabellako22/gifted_maths_gemma_4_gguf_v2 to start chatting

How to use arabellako22/gifted_maths_gemma_4_gguf_v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arabellako22/gifted_maths_gemma_4_gguf_v2: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": "arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use arabellako22/gifted_maths_gemma_4_gguf_v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arabellako22/gifted_maths_gemma_4_gguf_v2: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 arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use arabellako22/gifted_maths_gemma_4_gguf_v2 with Docker Model Runner:
```
docker model run hf.co/arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M
```

Lemonade

How to use arabellako22/gifted_maths_gemma_4_gguf_v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arabellako22/gifted_maths_gemma_4_gguf_v2:Q4_K_M

Run and chat with the model

lemonade run user.gifted_maths_gemma_4_gguf_v2-Q4_K_M

List all available models

lemonade list

Gifted Maths Gemma 4 GGUF

This is the verified GGUF version of maths_engine, a local gifted mathematics model designed for student-facing step-by-step LaTeX solutions.

Source

Base model: unsloth/gemma-4-E2B-it
LoRA adapter: arabellako22/gifted_maths_lora_model
Verified merged model: arabellako22/gifted_maths_unsloth_remerged_full_gemma_4
Dataset snapshot: arabellako22/gifted_maths_training_dataset

Files

gifted-maths-gemma-4-v2.Q4_K_M.gguf: recommended local version
gifted-maths-gemma-4-v2.Q5_K_M.gguf: slightly larger, usually better quality
Modelfile: Ollama-compatible template helper

Prompt Format

<start_of_turn>system
You are maths_engine, a local gifted mathematics reasoning model for students.
You solve maths problems step by step, clearly and calmly.
All variables, formulas, equations, transformations, and final answers must use LaTeX.
Use inline math with $...$ and display math with $$...$$.
Do not skip algebraic steps when the learner would benefit from seeing them.
End every solution with a clear line starting with: Final Answer:<end_of_turn>
<start_of_turn>user
Solve $2x^2+7x-4=0$ using the quadratic formula.<end_of_turn>
<start_of_turn>model

llama.cpp example

llama-cli \
  -m gifted-maths-gemma-4-v2.Q4_K_M.gguf \
  -p "<start_of_turn>system
You are maths_engine, a local gifted mathematics reasoning model for students.
You solve maths problems step by step, clearly and calmly.
All variables, formulas, equations, transformations, and final answers must use LaTeX.
Use inline math with $...$ and display math with $$...$$.
Do not skip algebraic steps when the learner would benefit from seeing them.
End every solution with a clear line starting with: Final Answer:<end_of_turn>
<start_of_turn>user
Solve $2x^2+7x-4=0$ using the quadratic formula.<end_of_turn>
<start_of_turn>model" \
  -n 900 \
  --temp 0

Verification Rule

This GGUF should not be considered complete unless:

base + adapter verification passes
merged full model verification passes
local GGUF verification passes
re-downloaded GGUF verification passes

Downloads last month: 183

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for arabellako22/gifted_maths_gemma_4_gguf_v2

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Finetuned

unsloth/gemma-4-E2B-it

Quantized

(18)

this model