Instructions to use spokenly/cleanup-1-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 spokenly/cleanup-1-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 spokenly/cleanup-1-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf spokenly/cleanup-1-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf spokenly/cleanup-1-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf spokenly/cleanup-1-gguf:Q8_0

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 spokenly/cleanup-1-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf spokenly/cleanup-1-gguf:Q8_0

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 spokenly/cleanup-1-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf spokenly/cleanup-1-gguf:Q8_0

Use Docker

docker model run hf.co/spokenly/cleanup-1-gguf:Q8_0

LM Studio
Jan

vLLM

How to use spokenly/cleanup-1-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spokenly/cleanup-1-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": "spokenly/cleanup-1-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spokenly/cleanup-1-gguf:Q8_0

Ollama
How to use spokenly/cleanup-1-gguf with Ollama:
```
ollama run hf.co/spokenly/cleanup-1-gguf:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use spokenly/cleanup-1-gguf with Docker Model Runner:
```
docker model run hf.co/spokenly/cleanup-1-gguf:Q8_0
```

Lemonade

How to use spokenly/cleanup-1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull spokenly/cleanup-1-gguf:Q8_0

Run and chat with the model

lemonade run user.cleanup-1-gguf-Q8_0

List all available models

lemonade list

Atomic Chat

Docs • Spokenly app • Main page • Core ML version • License

Spokenly Cleanup 1

This repository has the GGUF version of Spokenly Cleanup 1, a small language model that cleans up dictated text on the device. Spokenly, a dictation app, runs it with llama.cpp for Local Model Cleanup on Windows and Linux. On the Mac the app runs the Core ML version: spokenly/cleanup-1-coreml.

The model turns um so i think we should uh meet on friday at three pm into I think we should meet on Friday at 3 pm. More examples, the prompt format, the languages and the training data are on the main page.

Files

File	Contents
`cleanup-1-q8_0.gguf`	The model with 8-bit weights (Q8_0), 639 MB. The tokenizer is in the file

Model details

Property	Value
Base model	Qwen3-0.6B-Base, 0.6 B parameters
Fine-tuning	LoRA on all layers (rank 32), merged into the weights
Format	GGUF for llama.cpp with 8-bit weights (Q8_0)
Context	4,096 tokens for the prompt and the answer together
Decoding	Greedy
Speed	About 120 tokens per second on the processor alone, measured on a desktop Core i5-12400F with 6 cores. A dictation of one or two sentences takes about 0.3 seconds
Memory	About 650 MB while the model is loaded, up to 1.1 GB for the longest texts

How to use

The model works inside Spokenly on Windows and Linux. Open Settings > Behavior > Local Model Cleanup and switch on Clean up text with local model. Spokenly downloads the model once. On a PC with an Intel or AMD processor, the processor must have AVX2. See the documentation.

To run the file with llama.cpp, give the prompt as plain text and use greedy decoding:

llama-completion -m cleanup-1-q8_0.gguf --temp 0 -n 128 -no-cnv --no-display-prompt -p $'text: um so i think we should uh meet on friday at three pm\nout:'

The answer is I think we should meet on Friday at 3 pm. and then the end-of-text token.

Downloads last month: -

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

8-bit

Model tree for spokenly/cleanup-1-gguf

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

spokenly/cleanup-1

Quantized

(2)

this model