Instructions to use Level5Tech/clef-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Level5Tech/clef-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 Level5Tech/clef-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Level5Tech/clef-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 Level5Tech/clef-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Level5Tech/clef-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Level5Tech/clef-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Level5Tech/clef-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Level5Tech/clef-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Level5Tech/clef-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Level5Tech/clef-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": "Level5Tech/clef-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Level5Tech/clef-GGUF:Q4_K_M
- Ollama
How to use Level5Tech/clef-GGUF with Ollama:
ollama run hf.co/Level5Tech/clef-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use Level5Tech/clef-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Level5Tech/clef-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Level5Tech/clef-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Level5Tech/clef-GGUF with Docker Model Runner:
docker model run hf.co/Level5Tech/clef-GGUF:Q4_K_M
- Lemonade
How to use Level5Tech/clef-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Level5Tech/clef-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.clef-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Level5Tech/clef-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Level5Tech/clef-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default Level5Tech/clef-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Level5Tech/clef-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Level5Tech/clef-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "Level5Tech/clef-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Link the collection and the Zenodo archive, add the citation
Browse filesAdds the collection that holds the paper and all six builds, the Zenodo DOI, and the arXiv BibTeX.
README.md
CHANGED
|
@@ -16,4 +16,22 @@ Paper: https://arxiv.org/abs/2611.15671
|
|
| 16 |
|
| 17 |
Measurements, recipes and per-record outputs: https://github.com/Level5Tech/clef-quant-bench
|
| 18 |
|
| 19 |
-
The
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
Measurements, recipes and per-record outputs: https://github.com/Level5Tech/clef-quant-bench
|
| 18 |
|
| 19 |
+
The paper and all six builds, in one collection: https://huggingface.co/collections/Level5Tech/the-noise-floor-of-a-quantization-comparison-6afd62e8288cc5e14becefaf
|
| 20 |
+
|
| 21 |
+
Archived release (all versions): https://doi.org/10.5281/zenodo.24184497
|
| 22 |
+
|
| 23 |
+
The base model is under Apache-2.0. Its LICENSE is included here, and NOTICE says these weights were modified by quantization.
|
| 24 |
+
|
| 25 |
+
## Citation
|
| 26 |
+
|
| 27 |
+
```bibtex
|
| 28 |
+
@misc{blagojevich2026noisefloorquantizationcomparison,
|
| 29 |
+
title={The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models},
|
| 30 |
+
author={Aleks Blagojevich and Trevor Sunderland},
|
| 31 |
+
year={2026},
|
| 32 |
+
eprint={2611.15671},
|
| 33 |
+
archivePrefix={arXiv},
|
| 34 |
+
primaryClass={cs.LG},
|
| 35 |
+
url={https://arxiv.org/abs/2611.15671},
|
| 36 |
+
}
|
| 37 |
+
```
|