Instructions to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B", dtype="auto")

llama-cpp-python

How to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B",
	filename="claude-3.7-sonnet-reasoning-gemma3-12B.Q8_0.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 mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0
# Run inference directly in the terminal:
llama-cli -hf mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0
# Run inference directly in the terminal:
llama-cli -hf mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B: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 mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B: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 mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0

Use Docker

docker model run hf.co/mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0

LM Studio
Jan
Ollama
How to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with Ollama:
```
ollama run hf.co/mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0
```

Unsloth Studio

How to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B 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 mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B 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 mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B to start chatting

Docker Model Runner
How to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with Docker Model Runner:
```
docker model run hf.co/mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0
```

Lemonade

How to use mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mfielding92/claude-3.7-sonnet-reasoning-gemma3-12B:Q8_0

Run and chat with the model

lemonade run user.claude-3.7-sonnet-reasoning-gemma3-12B-Q8_0

List all available models

lemonade list

Uploaded Model

Overview

This model is a Gemma 3 12B variant specifically fine-tuned using reasoning data from Claude 3.7 Sonnet. The goal was to integrate Claude's acclaimed reasoning capabilities within a powerful, open-source architecture like Gemma.

Technical Details

Developed by: mfielding92
Base Model: google/gemma-3-12b
Finetuning Method: Supervised Fine-Tuning (SFT) using LoRA
Training Speed Enhancement: Trained 2x faster with Unsloth and Huggingface's TRL library

Training Data

The model was fine-tuned on a dataset derived from:

mfielding92/claude-3.7-sonnet-reasoning

This enables the model to potentially demonstrate superior logical reasoning, complex problem-solving, and analytical thinking compared to the standard Gemma 3 model, while remaining accessible and open-source.

Usage Notes

While this model incorporates some of Claude's reasoning strengths, it remains a derivative built on Gemma architecture. Users should thoroughly evaluate its performance for specific tasks and applications.

This Gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.