Instructions to use auswm85/flowbee-cut with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use auswm85/flowbee-cut 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 auswm85/flowbee-cut:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf auswm85/flowbee-cut:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf auswm85/flowbee-cut:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf auswm85/flowbee-cut: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 auswm85/flowbee-cut:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf auswm85/flowbee-cut: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 auswm85/flowbee-cut:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf auswm85/flowbee-cut:Q4_K_M

Use Docker

docker model run hf.co/auswm85/flowbee-cut:Q4_K_M

LM Studio
Jan

vLLM

How to use auswm85/flowbee-cut with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "auswm85/flowbee-cut"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "auswm85/flowbee-cut",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/auswm85/flowbee-cut:Q4_K_M

Ollama
How to use auswm85/flowbee-cut with Ollama:
```
ollama run hf.co/auswm85/flowbee-cut:Q4_K_M
```

Unsloth Studio

How to use auswm85/flowbee-cut with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for auswm85/flowbee-cut to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for auswm85/flowbee-cut to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for auswm85/flowbee-cut to start chatting

How to use auswm85/flowbee-cut with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf auswm85/flowbee-cut:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "auswm85/flowbee-cut:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use auswm85/flowbee-cut with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf auswm85/flowbee-cut: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 "auswm85/flowbee-cut: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"

Docker Model Runner
How to use auswm85/flowbee-cut with Docker Model Runner:
```
docker model run hf.co/auswm85/flowbee-cut:Q4_K_M
```

Lemonade

How to use auswm85/flowbee-cut with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull auswm85/flowbee-cut:Q4_K_M

Run and chat with the model

lemonade run user.flowbee-cut-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use auswm85/flowbee-cut with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf auswm85/flowbee-cut: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 auswm85/flowbee-cut:Q4_K_M

Run Hermes

hermes

Atomic Chat

flowbee-cut / README.md

auswm85

release v10-0dd3947: model card

5d58380 verified 14 days ago

preview code

Raw

History Blame Contribute Delete

3.29 kB

	---
	language:
	- en
	license: apache-2.0
	base_model: Qwen/Qwen3-4B-Instruct-2507
	pipeline_tag: text-generation
	tags:
	- gguf
	- transcript-cleaning
	- dictation
	- speech-to-text
	- llama.cpp
	model-index:
	- name: flowbee-cut
	results:
	- task:
	type: text-generation
	name: Transcript cleaning
	dataset:
	name: Flowbee Cut eval battery (held-out, 35 cases)
	type: flowbee-cut-battery
	metrics:
	- name: Battery pass rate
	type: accuracy
	value: 1.0000
	verified: false
	---

	# Flowbee Cut — technical dictation cleaner

	Fine-tune of [Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
	that cleans raw speech-to-text transcripts for [Flowbee](https://github.com/auswm85/flowbee),
	a local-first macOS dictation utility. It removes fillers and stutters,
	resolves self-corrections, and writes technical speech in its correct form:

	\| spoken \| written \|
	\| --------------------------------------- \| ------------------------- \|
	\| "rename it to camel case get user data" \| Rename it to getUserData. \|
	\| "run cargo test dash dash release" \| Run cargo test --release. \|
	\| "open main dot rs" \| Open main.rs. \|
	\| "we deploy behind engine x" \| We deploy behind nginx. \|

	This is not a chat model. It was trained to do exactly one thing under
	one system prompt, and it will clean — never answer — instruction-shaped
	transcripts ("write a unit test for the auth module" comes back as cleaned
	text, not a unit test).

	## Usage contract

	The model expects the exact Flowbee Cut system prompt it was trained with
	(the `coder` prompt in `scripts/cut-eval/prompts.mjs` of the Flowbee repo),
	with the raw transcript as the sole user message, `temperature 0`. Behavior
	under other prompts is untested. Serve with llama.cpp:

	```sh
	llama-server -m flowbee-cut-<version>.Q4_K_M.gguf -ngl 99 -c 4096
	```

	## Training

	- LoRA (r=16, attention projections, completion-only loss) on ~4,400
	synthetic pairs of messy spoken transcript → clean text: instruction-shaped
	technical dictation, CLI commands and flags, spoken identifiers and case
	directives, glossary-conditioned phonetic repairs, everyday dictation, and
	passthrough negatives. Adapter merged into the base weights, quantized to
	Q4_K_M.

	## Files

	- `flowbee-cut-<version>.Q4_K_M.gguf` — versioned releases (~2.5 GB).
	- `latest.json` — machine-read manifest (version, file, sha256, eval score).
	The Flowbee app checks it on startup and downloads new releases, verifying
	the sha256 before the file touches a GGUF parser. Do not rename or delete
	these files by hand.

	## Limitations

	- English only. Training data is English; the base model is multilingual
	but this fine-tune's behavior on non-English transcripts is untested.
	- Tuned for software-engineering vocabulary; exotic garbled jargon without a
	glossary hint is passed through verbatim by design (never deleted, never
	guessed).
	- Trained on synthetic data seeded with real dictation failures; expect
	occasional misses on unusual phrasing (e.g. a garbled term directly
	adjacent to a modifier).

	## License

	Apache-2.0