Instructions to use Hanish/quill-fix-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Hanish/quill-fix-v1 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 Hanish/quill-fix-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hanish/quill-fix-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hanish/quill-fix-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hanish/quill-fix-v1: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 Hanish/quill-fix-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hanish/quill-fix-v1: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 Hanish/quill-fix-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hanish/quill-fix-v1:Q4_K_M

Use Docker

docker model run hf.co/Hanish/quill-fix-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use Hanish/quill-fix-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Hanish/quill-fix-v1:Q4_K_M

Ollama
How to use Hanish/quill-fix-v1 with Ollama:
```
ollama run hf.co/Hanish/quill-fix-v1:Q4_K_M
```
Unsloth Desktop

How to use Hanish/quill-fix-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hanish/quill-fix-v1: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": "Hanish/quill-fix-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Hanish/quill-fix-v1 with Docker Model Runner:
```
docker model run hf.co/Hanish/quill-fix-v1:Q4_K_M
```

Lemonade

How to use Hanish/quill-fix-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hanish/quill-fix-v1:Q4_K_M

Run and chat with the model

lemonade run user.quill-fix-v1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Hanish/quill-fix-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hanish/quill-fix-v1: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 Hanish/quill-fix-v1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Hanish/quill-fix-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hanish/quill-fix-v1: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 "Hanish/quill-fix-v1: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"

Quill fix-v1

On-device grammar fix / voice-preserving rewrite model for Quill, a private AI keyboard and chat app. Fine-tuned from Qwen/Qwen3.5-0.8B-Base with LoRA (r=32, all projections) on 58.8k instruction rows (CoEdIT fix/rewrite, phone-style typo noising, 12% no-op rows) for 2 epochs. Merged and exported to GGUF with llama.cpp (convert_hf_to_gguf.py --no-nextn; EOS <|im_end|>).

File	Quant	Size	Use
`fix-v1-Q4_K_M.gguf`	Q4_K_M	529 MB	phones (4 GB+ RAM)
`fix-v1-Q8_0.gguf`	Q8_0	812 MB	higher precision

Prompt format (ChatML)

<|im_start|>system
You fix text typed on a phone. Keep the writer's voice exactly.
Fix only spelling, grammar, and punctuation. Never translate. Never add or remove sentences.
Output the corrected text only.
Voice: {profile}
Never change these words: {lexicon}<|im_end|>
<|im_start|>user
MODE=fix
in: {text}
out:<|im_end|>
<|im_start|>assistant

Modes: fix, rewrite tone={casual|neutral|formal|shorter|longer}.

Held-out eval (150 rows, vs zero-shot base)

exact-match 9% → 43% · GLEU-lite 0.32 → 0.73 · no-op precision 33% → 94% · over-edit rate 43% → 24%.

Example: i dont think were gonna make it on time, traffic is crazy rn → I don't think we're gonna make it on time, traffic is crazy rn.

Requires llama.cpp with the qwen35 architecture (2026-05 or newer).

Downloads last month: 43

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

8-bit

Model tree for Hanish/quill-fix-v1

Base model

Qwen/Qwen3.5-0.8B-Base

Quantized

(42)

this model