Instructions to use tinyopsec/Pythagoras-Prover-4B-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 tinyopsec/Pythagoras-Prover-4B-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 tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tinyopsec/Pythagoras-Prover-4B-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 tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tinyopsec/Pythagoras-Prover-4B-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 tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use tinyopsec/Pythagoras-Prover-4B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tinyopsec/Pythagoras-Prover-4B-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": "tinyopsec/Pythagoras-Prover-4B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
- Ollama
How to use tinyopsec/Pythagoras-Prover-4B-GGUF with Ollama:
ollama run hf.co/tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use tinyopsec/Pythagoras-Prover-4B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tinyopsec/Pythagoras-Prover-4B-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": "tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use tinyopsec/Pythagoras-Prover-4B-GGUF with Docker Model Runner:
docker model run hf.co/tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
- Lemonade
How to use tinyopsec/Pythagoras-Prover-4B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Pythagoras-Prover-4B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use tinyopsec/Pythagoras-Prover-4B-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 tinyopsec/Pythagoras-Prover-4B-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 tinyopsec/Pythagoras-Prover-4B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use tinyopsec/Pythagoras-Prover-4B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tinyopsec/Pythagoras-Prover-4B-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 "tinyopsec/Pythagoras-Prover-4B-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"
Q8_0 vs Q6_K on RTX 3060: decode, prefill and perplexity on Lean 4 source
Measured both quants on a single RTX 3060 12 GB (llama.cpp CUDA build, -ngl 99, 3 reps).
Posting in case it saves someone a download.
| quant | size | pp512 (t/s) | tg128 (t/s) |
|---|---|---|---|
| Q8_0 | 4.37 GiB | 3654 ± 244 | 68.8 ± 0.1 |
| Q6_K | 3.37 GiB | 2724 ± 724 | 80.6 ± 0.2 |
Decode is +17% for Q6_K, not the ~+29% that pure memory-bandwidth scaling predicts from
4.69 GB vs 3.62 GB. Q8_0 dequantization is largely free on tensor cores, while K-quants pay a
real per-weight dequantization cost — so the usual "size ratio = speed ratio" rule
overestimates K-quant gains on this card.
Prefill is -25% for Q6_K. On a 512-token prompt that is 140 ms vs 188 ms, so it only
matters when prompts get long.
Perplexity on an identical corpus (95 KB of Lean 4 source, 7 chunks, n_ctx 4096):
- Q8_0: 2.4012 ± 0.0428
- Q6_K: 2.4165 ± 0.0431
Difference +0.64%, i.e. inside one standard error. No detectable quality loss at this sample
size — though this only rules out gross degradation, it says nothing about downstream proving
ability.
Prover sanity check (Q8_0 only): 14 problems sampled from MiniF2F-test, 4 samples each,
temperature 0.7, every proof verified by Lean 4.25.0 — 9 of 14 solved (pass@4 = 64%).
Small sample and not comparable to the model card's pass@32 figure; included only to confirm
the quant is functional as a prover and not just as a language model.
Practical conclusion for a 4B prover on a 12 GB card: decode dominates the wall clock, so
Q6_K is the faster choice end to end (~15% on a 2000-token proof), while Q8_0 wins on prefill
and is the safer pick if quality is the only consideration. Both fit four 16k context slots.