Instructions to use Hanish/quill-models 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-models 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-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hanish/quill-models: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-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hanish/quill-models: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-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hanish/quill-models: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-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hanish/quill-models:Q4_K_M

Use Docker

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

LM Studio
Jan
Ollama
How to use Hanish/quill-models with Ollama:
```
ollama run hf.co/Hanish/quill-models:Q4_K_M
```
Unsloth Desktop

How to use Hanish/quill-models 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-models: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-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use Hanish/quill-models with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.quill-models-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Hanish/quill-models 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-models: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-models:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Hanish/quill-models 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-models: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-models: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 on-device chat models (GGUF mirror)

Byte-identical mirrors of upstream GGUF files used by the Quill app (offline chat + AI keyboard, Android). Nothing here is modified or fine-tuned; the mirror exists so the app's downloads do not depend on upstream repo names. Quill's own keyboard model lives in Hanish/quill-fix-v1.

File	Model	Quant	Size	Upstream GGUF	Soft RAM floor in Quill
`Qwen3.5-0.8B-Q4_K_M.gguf`	Qwen3.5-0.8B (instruct)	Q4_K_M	533 MB	unsloth/Qwen3.5-0.8B-GGUF	3 GB ("Chat Lite")
`Qwen3.5-2B-Q4_K_M.gguf`	Qwen3.5-2B (instruct)	Q4_K_M	1.28 GB	unsloth/Qwen3.5-2B-GGUF	5 GB ("Chat")
`gemma-4-E2B-it-Q4_0.gguf`	Gemma 4 E2B (instruct)	Q4_0	2.84 GB	ggml-org/gemma-4-E2B-it-GGUF	7 GB ("Chat Pro")

sha256 (also pinned in the app):

bd258782e35f7f458f8aced1adc053e6e92e89bc735ba3be89d38a06121dc517  Qwen3.5-0.8B-Q4_K_M.gguf
aaf42c8b7c3cab2bf3d69c355048d4a0ee9973d48f16c731c0520ee914699223  Qwen3.5-2B-Q4_K_M.gguf
8e30dff3ac4c8434c49a7036fa15564bdbb6044e42bf04550bf1a096ad7e6a52  gemma-4-E2B-it-Q4_0.gguf

Licenses and credit

Runs with llama.cpp (MIT). Quill uses build b6b003d or newer (qwen35 and gemma4 architectures).

Prompt formats used by Quill

Qwen3.5: ChatML with an empty <think>\n\n</think> block after <|im_start|>assistant (thinking off).
Gemma 4: <bos><start_of_turn>user\n{system}\n\n{user}<end_of_turn>\n<start_of_turn>model\n.

Downloads last month: 11

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Hanish/quill-models

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(259)

this model