Instructions to use MCES10/maths-problems-gemma-2-2b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MCES10/maths-problems-gemma-2-2b-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MCES10/maths-problems-gemma-2-2b-it-GGUF",
	filename="maths-problems-gemma-2-2B-it-F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MCES10/maths-problems-gemma-2-2b-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 MCES10/maths-problems-gemma-2-2b-it-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MCES10/maths-problems-gemma-2-2b-it-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

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 MCES10/maths-problems-gemma-2-2b-it-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

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 MCES10/maths-problems-gemma-2-2b-it-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

Use Docker

docker model run hf.co/MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

LM Studio
Jan

vLLM

How to use MCES10/maths-problems-gemma-2-2b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MCES10/maths-problems-gemma-2-2b-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": "MCES10/maths-problems-gemma-2-2b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

Ollama
How to use MCES10/maths-problems-gemma-2-2b-it-GGUF with Ollama:
```
ollama run hf.co/MCES10/maths-problems-gemma-2-2b-it-GGUF:F16
```

Unsloth Studio new

How to use MCES10/maths-problems-gemma-2-2b-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 MCES10/maths-problems-gemma-2-2b-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 MCES10/maths-problems-gemma-2-2b-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 MCES10/maths-problems-gemma-2-2b-it-GGUF to start chatting

Docker Model Runner
How to use MCES10/maths-problems-gemma-2-2b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/MCES10/maths-problems-gemma-2-2b-it-GGUF:F16
```

Lemonade

How to use MCES10/maths-problems-gemma-2-2b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MCES10/maths-problems-gemma-2-2b-it-GGUF:F16

Run and chat with the model

lemonade run user.maths-problems-gemma-2-2b-it-GGUF-F16

List all available models

lemonade list

Maths Problem Solving AI Based on Google Gemma 2 2b it GGUF

Based on OpenR1-Math-220k

Input:

A ship traveling along a river has covered $24 \mathrm{km}$ upstream and $28 \mathrm{km}$ downstream. For this journey, it took half an hour less than for traveling $30 \mathrm{km}$ upstream and $21 \mathrm{km}$ downstream, or half an hour more than for traveling $15 \mathrm{km}$ upstream and $42 \mathrm{km}$ downstream, assuming that both the ship and the river move uniformly. Determine the speed of the ship in still water and the speed of the river.

Output:

Here's how to solve this problem:

Let's denote:

x = speed of the ship in still water
y = speed of the river

Formulate the equations:

Upstream: x - y = x / 2 (The ship travels against the current, so its speed is reduced)
Downstream: x + y = x / 2 (The ship travels with the current, so its speed is increased)

Solve the system of equations:

Simplify the equations:
- x - y = x/2 => x - x/2 = y => x/2 = y
- x + y = x/2 => x + x/2 = y => 3x/2 = y
Substitute the value of y from the first equation into the second equation:
- x/2 = 3x/2
Solve for x:
- x = 0
Substitute the value of x back into the equation for y:
- y = 0

Answer:

The speed of the ship in still water is 0 km/h.
The speed of the river is 0 km/h.

Conclusion:

The ship is stationary, and the river is also stationary. This means that the ship and the river are at rest relative to each other.

========== Prompt: 114 tokens, 417.293 tokens-per-sec Generation: 358 tokens, 28.375 tokens-per-sec Peak memory: 5.406 GB

Downloads last month: 16

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

16-bit

Dataset used to train MCES10/maths-problems-gemma-2-2b-it-GGUF

Collection including MCES10/maths-problems-gemma-2-2b-it-GGUF

Gemma 2 2B it

Collection

Fine tuned Gemma 2 2b it models • 4 items • Updated May 13, 2025 • 1