Instructions to use cstr/Spaetzle-v12-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use cstr/Spaetzle-v12-7b-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 cstr/Spaetzle-v12-7b-GGUF
# Run inference directly in the terminal:
llama cli -hf cstr/Spaetzle-v12-7b-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cstr/Spaetzle-v12-7b-GGUF
# Run inference directly in the terminal:
llama cli -hf cstr/Spaetzle-v12-7b-GGUF

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 cstr/Spaetzle-v12-7b-GGUF
# Run inference directly in the terminal:
./llama-cli -hf cstr/Spaetzle-v12-7b-GGUF

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 cstr/Spaetzle-v12-7b-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cstr/Spaetzle-v12-7b-GGUF

Use Docker

docker model run hf.co/cstr/Spaetzle-v12-7b-GGUF

LM Studio
Jan
Ollama
How to use cstr/Spaetzle-v12-7b-GGUF with Ollama:
```
ollama run hf.co/cstr/Spaetzle-v12-7b-GGUF
```

Unsloth Studio

How to use cstr/Spaetzle-v12-7b-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 cstr/Spaetzle-v12-7b-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 cstr/Spaetzle-v12-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cstr/Spaetzle-v12-7b-GGUF to start chatting

Docker Model Runner
How to use cstr/Spaetzle-v12-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/cstr/Spaetzle-v12-7b-GGUF
```

Lemonade

How to use cstr/Spaetzle-v12-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cstr/Spaetzle-v12-7b-GGUF

Run and chat with the model

lemonade run user.Spaetzle-v12-7b-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Spaetzle-v12-7b — GGUF

GGUF conversion of cstr/Spaetzle-v12-7b. Spaetzle v12 German 7B fine-tune.

Files

File	Size
`Spaetzle-v12-7b-q4-k-m.gguf`	4166 MB

Compatible with llama.cpp and other GGUF runtimes.

Provenance and EU AI Act Art. 53 note

Base model: cstr/Spaetzle-v12-7b — a mergekit merge published by the same maintainer as this repository. It is not a third-party upstream: the maintainer authored that model.
What was done here: format conversion and/or quantisation of that base model only (GGUF). No further training, fine-tuning or merging was applied at this step.
Licence: llama2, inherited through the base model from the models it was built from.
Training data: none was used, added or selected at this conversion step. The base model's card lists the models it was built from; their training content is documented — where it is documented at all — by their respective providers.
Provider status: under Regulation (EU) 2024/1689 this repository makes no provider claim for the conversion step. Any provider obligations attaching to the model itself — including Art. 53(1)(c) copyright policy and Art. 53(1)(d) training-content summary — attach at cstr/Spaetzle-v12-7b, not here.

Licence — corrected 2026-08-02. cc-by-sa-4.0, inherited from cstr/Spaetzle-v12-7b, which contains ResplendentAI/Flora_DPO_7B (CC-BY-SA-4.0). This card previously declared llama2, which is doubly wrong: the base is a Mistral merge, not a Llama one.

Quantisation changes the numeric representation of the weights, not their terms. The base model's licence was itself resolved on 2026-08-02 by reading the mergekit configuration in its card and taking the most restrictive constituent licence; this file inherits the result.