Instructions to use breitburg/pure-reasoning-7b-230726-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use breitburg/pure-reasoning-7b-230726-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="breitburg/pure-reasoning-7b-230726-GGUF",
	filename="pure-reasoning-7b-230726.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 breitburg/pure-reasoning-7b-230726-GGUF 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 breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf breitburg/pure-reasoning-7b-230726-GGUF: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 breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf breitburg/pure-reasoning-7b-230726-GGUF: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 breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M

Use Docker

docker model run hf.co/breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use breitburg/pure-reasoning-7b-230726-GGUF with Ollama:
```
ollama run hf.co/breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M
```

Unsloth Studio

How to use breitburg/pure-reasoning-7b-230726-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 breitburg/pure-reasoning-7b-230726-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 breitburg/pure-reasoning-7b-230726-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for breitburg/pure-reasoning-7b-230726-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use breitburg/pure-reasoning-7b-230726-GGUF with Docker Model Runner:
```
docker model run hf.co/breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M
```

Lemonade

How to use breitburg/pure-reasoning-7b-230726-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull breitburg/pure-reasoning-7b-230726-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.pure-reasoning-7b-230726-GGUF-Q4_K_M

List all available models

lemonade list

pure-reasoning-7b-230726-GGUF

GGUF build of breitburg/pure-reasoning-7b-230726, a thinking model that emits a <think>...</think> block then an answer. Converted 23 July 2026 with Unsloth. The ChatML chat template is embedded in the GGUF, so pass --jinja.

Example usage:

llama-cli -hf breitburg/pure-reasoning-7b-230726-GGUF:Q8_0 --jinja

Available files

pure-reasoning-7b-230726.Q8_0.gguf — ~7.2 GB, higher quality
pure-reasoning-7b-230726.Q4_K_M.gguf — ~4 GB, smaller/faster

Trained 2x faster with Unsloth.

Downloads last month: 197

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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

Collection including breitburg/pure-reasoning-7b-230726-GGUF

Pure

Collection

AI-contamination-free foundation for alignment and persona-modeling research • 6 items • Updated 4 days ago