Instructions to use scribekey/scribekey-cleanup-fast-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 scribekey/scribekey-cleanup-fast-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 scribekey/scribekey-cleanup-fast-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf scribekey/scribekey-cleanup-fast-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf scribekey/scribekey-cleanup-fast-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf scribekey/scribekey-cleanup-fast-GGUF:Q8_0

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 scribekey/scribekey-cleanup-fast-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf scribekey/scribekey-cleanup-fast-GGUF:Q8_0

Use Docker

docker model run hf.co/scribekey/scribekey-cleanup-fast-GGUF:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use scribekey/scribekey-cleanup-fast-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "scribekey/scribekey-cleanup-fast-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": "scribekey/scribekey-cleanup-fast-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/scribekey/scribekey-cleanup-fast-GGUF:Q8_0

Ollama
How to use scribekey/scribekey-cleanup-fast-GGUF with Ollama:
```
ollama run hf.co/scribekey/scribekey-cleanup-fast-GGUF:Q8_0
```
Unsloth Desktop

How to use scribekey/scribekey-cleanup-fast-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf scribekey/scribekey-cleanup-fast-GGUF:Q8_0

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": "scribekey/scribekey-cleanup-fast-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use scribekey/scribekey-cleanup-fast-GGUF with Docker Model Runner:
```
docker model run hf.co/scribekey/scribekey-cleanup-fast-GGUF:Q8_0
```

Lemonade

How to use scribekey/scribekey-cleanup-fast-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull scribekey/scribekey-cleanup-fast-GGUF:Q8_0

Run and chat with the model

lemonade run user.scribekey-cleanup-fast-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use scribekey/scribekey-cleanup-fast-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 scribekey/scribekey-cleanup-fast-GGUF:Q8_0

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 scribekey/scribekey-cleanup-fast-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use scribekey/scribekey-cleanup-fast-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf scribekey/scribekey-cleanup-fast-GGUF:Q8_0

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 "scribekey/scribekey-cleanup-fast-GGUF:Q8_0" \
  --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"

ScribeKey Fast by ScribeKey — GGUF

The evaluated Q8_0 build of ScribeKey Fast, a 350M-class English speech-to-text cleanup model. It receives a transcript, not audio, and returns cleaned text. It is not a general chat assistant.

Release v1.1. It replaces v1 (still available at the v1 tag) with better handling of spoken self-corrections; architecture, size, prompt and controls are unchanged. Phone latency and memory of this exact file have not been measured yet. Two public-input BF16 CPU smoke cases ran twice with identical outputs (bf16-smoke.json); this is an inference check, not a BF16 quality benchmark.

File	Bytes	SHA-256
`scribekey-cleanup-fast-350m-v1.1-Q8_0.gguf`	379,219,904 (361.7 MiB)	`2dfd7463ae0a8ca7dd2e4abebeed9cc77a584569b9c99dc9e68ad85f1399b55a`

Converted and quantized with llama.cpp 4c1a0af40d88c7fbb3b15c85bf2e8016d1d5b64c, ScribeKey's runtime pin. Only the download filename changed; the evaluated bytes and internal experiment metadata are preserved. Lower-bit files have not been included because they have not been evaluated.

Run it

Use raw completion mode and the exact task prompt. The evaluated GGUF retains an inherited LFM chat template; do not rely on its automatic chat formatting. prompt-template.jinja is a separate task-specific template for integrations that support overriding the embedded template.

llama-server -m scribekey-cleanup-fast-350m-v1.1-Q8_0.gguf \
  --host 127.0.0.1 --port 8080 -c 4096 -t 2 --temp 0 --seed 42

import json
import urllib.request

raw = "um can you send the updated agenda before lunch"
control = "[Styling: semi-casual] [Structure: prose] [Context: general]"
prompt = f"<|startoftext|>### Input:\n{control}\n{raw}\n\n### Output:\n"
request = urllib.request.Request(
    "http://127.0.0.1:8080/completion",
    data=json.dumps({
        "prompt": prompt, "n_predict": 256, "temperature": 0,
        "top_k": 1, "top_p": 1.0, "repeat_penalty": 1.0, "seed": 42,
        "stop": ["###", "<|im_end|>"],
    }).encode(),
    headers={"Content-Type": "application/json"},
)
with urllib.request.urlopen(request, timeout=60) as response:
    print(json.load(response)["content"].strip())

Use one BOS, no system message, no thinking mode and greedy decoding. Controls are styling (casual, semi-casual, semi-formal, formal), structure (prose, lists) and context (general, email). ScribeKey uses semi-casual/prose by default, semi-formal/email in email apps, and performs list formatting in the app after generation.

Evidence and limitations

On ScribeKey's frozen held-out set (7,516 rows), paired against v1 under semi-casual/prose/general at the app boundary, v1.1 lowers the self-correction token edit rate by 0.036 (95% −0.046 to −0.026) and raises exact match by 3.3 points (+2.4 to +4.3). Clean-input changes (−0.9 points) and new factual values (−0.3 points, −0.7 to +0.1) are no worse than v1. Names, numbers, negations and omissions still need checking.

Phone latency and memory of this file are not measured; v1, with the same architecture and file size, measured short p50/p95 155/178 ms and long 1,702/2,718 ms on an S25 Ultra. See evaluation.json, examples.json and the full model card for scope and known limits. Keep raw transcripts and a fallback; output is not guaranteed faithful. Lists and email layout can also be wrong.

Terms and attribution

The weights inherit LFM Open License v1.0, including its commercial revenue condition, not a blanket Apache or MIT licence. Retain ADDITIONAL_TERMS.md, LICENSE, NOTICE and MODIFICATIONS.md when redistributing and mark your changes. Organisations at or above the licence's US$10M annual-revenue threshold should obtain separate terms from Liquid AI before commercial use. Read section 5; this summary is not a legal opinion.

ScribeKey Fast continues Sotto by juanquivilla, based on LFM2.5-350M-Base by Liquid AI. NOTICE preserves Sotto's MIT notice and credits the training sources, including CC BY/CC BY-SA data. Those source terms remain distinct; this card does not resolve whether share-alike reaches model weights. Source text/audio and hidden benchmark rows are not distributed. The inherited Sotto data history has not been independently reconstructed. No upstream endorsement is implied. The ScribeKey Fast Model Terms v1.0 require the ScribeKey Fast name and ScribeKey publisher credit in model selectors/information and documentation; modified derivatives must credit Derived from ScribeKey Fast by ScribeKey.

v1.1 replaces the weights of v1; terms, prompt and runtime controls are unchanged. The v1 and RC tags are preserved.