Instructions to use StandardThinking/StandardOne-3B-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 StandardThinking/StandardOne-3B-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 StandardThinking/StandardOne-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf StandardThinking/StandardOne-3B-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 StandardThinking/StandardOne-3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf StandardThinking/StandardOne-3B-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 StandardThinking/StandardOne-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf StandardThinking/StandardOne-3B-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 StandardThinking/StandardOne-3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf StandardThinking/StandardOne-3B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/StandardThinking/StandardOne-3B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use StandardThinking/StandardOne-3B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "StandardThinking/StandardOne-3B-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": "StandardThinking/StandardOne-3B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/StandardThinking/StandardOne-3B-GGUF:Q4_K_M
- Ollama
How to use StandardThinking/StandardOne-3B-GGUF with Ollama:
ollama run hf.co/StandardThinking/StandardOne-3B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use StandardThinking/StandardOne-3B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf StandardThinking/StandardOne-3B-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:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "StandardThinking/StandardOne-3B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use StandardThinking/StandardOne-3B-GGUF with Docker Model Runner:
docker model run hf.co/StandardThinking/StandardOne-3B-GGUF:Q4_K_M
- Lemonade
How to use StandardThinking/StandardOne-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull StandardThinking/StandardOne-3B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.StandardOne-3B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use StandardThinking/StandardOne-3B-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 StandardThinking/StandardOne-3B-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://127.0.0.1:8080/v1 hermes config set model.default StandardThinking/StandardOne-3B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use StandardThinking/StandardOne-3B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf StandardThinking/StandardOne-3B-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://127.0.0.1:8080/v1 \ --custom-model-id "StandardThinking/StandardOne-3B-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"
Download systemone-validation.json from StandardThinking/StandardOne-3B-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 12.7 kB
-
https://huggingface.co/StandardThinking/StandardOne-3B-GGUF/resolve/main/systemone-validation.json
- Command line
-
hf download hf://StandardThinking/StandardOne-3B-GGUF/systemone-validation.json
-
curl -L -o systemone-validation.json https://huggingface.co/StandardThinking/StandardOne-3B-GGUF/resolve/main/systemone-validation.json
12.7 kB
| { | |
| "date": "2026-10-08", | |
| "weight_version": "v2.2", | |
| "runtime": "llama.cpp b11495 / 37ac63456, Linux x86_64, CPU, four threads", | |
| "runtime_archive_sha256": "e9272c922c2e098d55ec39c0616b8f545984978a7b61fec8ed1fc312925a27c2", | |
| "temperatures": { | |
| "choice": 0.9, | |
| "noul": 1.15, | |
| "score": 1.2 | |
| }, | |
| "added_metadata_keys": [ | |
| "mistral3.decision.type", | |
| "tokenizer.chat_template.systemone", | |
| "mistral3.decision.temperature.choice", | |
| "mistral3.decision.temperature.noul", | |
| "mistral3.decision.temperature.score" | |
| ], | |
| "method": "Compare native /v1/systemone against /completion pre-sampling option logprobs using identical prompts and verified one-token labels; softmax at per-type temperatures. Individual slots cleared before each request; multi-question reference calls execute in the native question order and preserve prefix state after the first question.", | |
| "single_call_probability_tolerance": 5e-05, | |
| "multi_question_probability_tolerance": 5e-05, | |
| "files": { | |
| "StandardOne-3B-BF16.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 3.4035333301707382e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 1.895569257115426e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 7.564064152809635e-09, | |
| "max_expected_score_error": 9.852553439770873e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 2.2212667642740325e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 1.3041013243245136e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 6.924828266363647e-09, | |
| "max_expected_score_error": 9.041088988581691e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-IQ2_M.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 3.4227816525511656e-08, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 2.8620783520949544e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 6.059652571388519e-10, | |
| "max_expected_score_error": 5.536675562467508e-10 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 3.0364000203064734e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 2.0019862278369827e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 3.4227816525511656e-08, | |
| "max_expected_score_error": 3.2945264294426124e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-IQ3_M.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 1.2602752313961574e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 1.7948651453991715e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 2.3118781333764105e-09, | |
| "max_expected_score_error": 3.1876872252922794e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 7.9271381125956e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 4.368192500422974e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 5.521665680241483e-09, | |
| "max_expected_score_error": 7.26999127564909e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-IQ4_XS.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 8.738536894092874e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 1.1185221637788345e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 1.5589824986506073e-09, | |
| "max_expected_score_error": 2.221572259486493e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 2.9374810899679415e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 1.5319889419551647e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 8.738536894092874e-09, | |
| "max_expected_score_error": 6.359697213298432e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-Q2_K.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 7.071243257605886e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 4.934683772717108e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 9.269061851391314e-09, | |
| "max_expected_score_error": 9.514000698374048e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 1.3465061704520664e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 3.3744141925140525e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 7.071243257605886e-09, | |
| "max_expected_score_error": 5.828444615829653e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-Q3_K_M.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 6.604746860539024e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 1.0567493546886908e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 8.310530485999834e-09, | |
| "max_expected_score_error": 1.1104013930562928e-08 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 1.1127920807041392e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 2.25361262984336e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 7.031610960162027e-09, | |
| "max_expected_score_error": 9.352805641071882e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-Q4_K_M.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 2.749427241433011e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 4.159056432584407e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 8.781075866437504e-10, | |
| "max_expected_score_error": 1.3451164626587797e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 4.449257628991177e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 1.0385021878903111e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 3.2670162131154257e-09, | |
| "max_expected_score_error": 5.518938639426096e-10 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-Q5_K_M.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 9.42021446959096e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 2.287422473656875e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 3.6667280323143814e-09, | |
| "max_expected_score_error": 4.8813184605478455e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 1.5826660069301335e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 9.424254493115014e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 1.8404174850772392e-09, | |
| "max_expected_score_error": 2.23601959170594e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| }, | |
| "StandardOne-3B-Q8_0.gguf": { | |
| "passed": true, | |
| "cases": [ | |
| { | |
| "name": "choice", | |
| "status": 200, | |
| "max_probability_error": 1.8004621349376748e-08, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "noul", | |
| "status": 200, | |
| "max_probability_error": 2.260874265580526e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "score", | |
| "status": 200, | |
| "max_probability_error": 7.16143355727894e-09, | |
| "max_expected_score_error": 9.318077864861607e-09 | |
| }, | |
| { | |
| "name": "structured-state", | |
| "status": 200, | |
| "max_probability_error": 3.367551348887332e-09, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "reversed-key-order", | |
| "status": 200, | |
| "max_probability_error": 4.823325940039869e-10, | |
| "max_expected_score_error": 0.0 | |
| }, | |
| { | |
| "name": "multi", | |
| "status": 200, | |
| "max_probability_error": 1.8004621349376748e-08, | |
| "max_expected_score_error": 7.562626969104258e-09 | |
| } | |
| ], | |
| "output_tokens": 0 | |
| } | |
| }, | |
| "limits": [ | |
| "native wording, <=26 options", | |
| "text only; no GPU or image validation", | |
| "not served preset with temperature 1.65 or extended labels", | |
| "state object key order preserved, not sorted as in jev-adapter", | |
| "llama.cpp confidence is not adapter entropy confidence", | |
| "API/probability parity fixtures, not task accuracy or calibration benchmark" | |
| ], | |
| "cold_prefill_comparison_note": { | |
| "artifact": "StandardOne-3B-Q4_K_M.gguf", | |
| "observed_noul_difference": 0.0012071734712206794, | |
| "reason": "Native multi-question requests preserve prefix cache between questions; clearing the cache before every reference question changes CPU batching. The validated reference follows the same cache reuse order without modifying the runtime." | |
| } | |
| } | |