Instructions to use rappidAI/quantum-1.6-pilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rappidAI/quantum-1.6-pilot with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rappidAI/quantum-1.6-pilot",
	filename="quantum-1.6-pilot-v1.6.0-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use rappidAI/quantum-1.6-pilot 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 rappidAI/quantum-1.6-pilot:F16
# Run inference directly in the terminal:
llama cli -hf rappidAI/quantum-1.6-pilot:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rappidAI/quantum-1.6-pilot:F16
# Run inference directly in the terminal:
llama cli -hf rappidAI/quantum-1.6-pilot: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 rappidAI/quantum-1.6-pilot:F16
# Run inference directly in the terminal:
./llama-cli -hf rappidAI/quantum-1.6-pilot: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 rappidAI/quantum-1.6-pilot:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rappidAI/quantum-1.6-pilot:F16

Use Docker

docker model run hf.co/rappidAI/quantum-1.6-pilot:F16

LM Studio
Jan

vLLM

How to use rappidAI/quantum-1.6-pilot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rappidAI/quantum-1.6-pilot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rappidAI/quantum-1.6-pilot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rappidAI/quantum-1.6-pilot:F16

Ollama
How to use rappidAI/quantum-1.6-pilot with Ollama:
```
ollama run hf.co/rappidAI/quantum-1.6-pilot:F16
```

Unsloth Studio

How to use rappidAI/quantum-1.6-pilot 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 rappidAI/quantum-1.6-pilot 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 rappidAI/quantum-1.6-pilot to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rappidAI/quantum-1.6-pilot to start chatting

Atomic Chat new
Docker Model Runner
How to use rappidAI/quantum-1.6-pilot with Docker Model Runner:
```
docker model run hf.co/rappidAI/quantum-1.6-pilot:F16
```

Lemonade

How to use rappidAI/quantum-1.6-pilot with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rappidAI/quantum-1.6-pilot:F16

Run and chat with the model

lemonade run user.quantum-1.6-pilot-F16

List all available models

lemonade list

Quantum 1.6 Pilot – GGUF

Quantum 1.6 Pilot ist ein experimentelles deutsches Base-Modell aus dem Lumen-Projekt.

Modell

Architektur: LlamaForCausalLM
Parameter: 49.295.872
Kontextlänge: 512 Tokens
Sprache: überwiegend Deutsch
Format: GGUF
Quantisierung: F16
Inferenz: llama.cpp-kompatibel
Status: Experimental Base Model

Training

Quantum 1.6 Pilot wurde als Continued-Pretraining aus Quantum 1 Base erzeugt.

Ausgangsmodell: Quantum 1 Base
Bestehendes Training: etwa 100 Mio. Tokens
Zusätzliches Training: 500 Mio. neue deutsche Tokens
Gesamtumfang: etwa 600 Mio. Tokens
Tokenizer: eingefrorener quantum-1 Tokenizer
Kein vortrainiertes Fremdmodell als Ausgangsgewicht verwendet

Evaluation

Validation Loss: 3.348852
Perplexity: 28.4700
Validation Tokens: rund 1.996.093

Wichtiger Hinweis

Dies ist weiterhin ein Base-Completion-Modell, kein Chat- oder Instruction-Modell.

Es kann Text fortsetzen, ist aber nicht zuverlässig für Faktenfragen, Gespräche, Anweisungen oder sicherheitskritische Inhalte. Antworten können falsch, unvollständig oder zusammenhanglos sein.

Dateien

Datei	Zweck
`quantum-1.6-pilot-v1.6.0-f16.gguf`	Lauffähiges GGUF-F16-Modell
`manifest.json`	Metadaten für die Lumen-Android-App
`SHA256SUMS.txt`	Integritätsprüfung

SHA-256:

6bda15fcd51286e55174d5876fe44aa9518fb18b75fb5aa4f7402ebd039bd994

Downloads last month: 18

GGUF

Model size

49.3M params

Architecture

llama

Hardware compatibility

16-bit