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

Use Docker

docker model run hf.co/datadab/writeamp-models:Q4_K_M

LM Studio
Jan

vLLM

How to use datadab/writeamp-models with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/datadab/writeamp-models:Q4_K_M

Ollama
How to use datadab/writeamp-models with Ollama:
```
ollama run hf.co/datadab/writeamp-models:Q4_K_M
```

Unsloth Studio

How to use datadab/writeamp-models 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 datadab/writeamp-models 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 datadab/writeamp-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for datadab/writeamp-models to start chatting

How to use datadab/writeamp-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datadab/writeamp-models: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": "datadab/writeamp-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use datadab/writeamp-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datadab/writeamp-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 "datadab/writeamp-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"

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

Lemonade

How to use datadab/writeamp-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull datadab/writeamp-models:Q4_K_M

Run and chat with the model

lemonade run user.writeamp-models-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use datadab/writeamp-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 datadab/writeamp-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 datadab/writeamp-models:Q4_K_M

Run Hermes

hermes

Atomic Chat

WriteAmp's on-device model catalog

This repository hosts WriteAmp's downloadable model artifacts. The catalog has three tiers (mini, midi, max); two of them are mirrors of upstream Q4_K_M quantizations, one is a custom Hinglish fine-tune.

Tier	File	Size	SHA-256	Source
`mini`	`mini/SmolLM2-135M.Q4_K_M.gguf`	105,454,016 B	`127c52bae983b2d0de09c60d6292743e3239e44239bbe8ccb8cf3241513ff5a0`	Mirror of `mradermacher/SmolLM2-135M-GGUF` (Apache 2.0)
`midi`	`midi/SmolLM2-360M.Q4_K_M.gguf`	270,590,464 B	`4ac7aa712c43fe7d07ed910298b5eaab932292692954abd8e0703307724e4e04`	Mirror of `mradermacher/SmolLM2-360M-GGUF` (Apache 2.0)
`max`	`WriteAmp-Qwen3-0.6B-Hinglish-v3.Q4_K_M.gguf`	396,704,544 B	`98df7dd1daaf65602fa002733d5c5a32527acd174730b591235f0ed170f17185`	Custom QLoRA fine-tune of `Qwen/Qwen3-0.6B-Base` (Apache 2.0)

Each tier's mirror card (under mini/ and midi/) carries provenance and license details. The max tier's full description, training data, and known limitations are in WriteAmp-Qwen3-0.6B-Hinglish-v3.Q4_K_M.gguf's card above.

Mirroring policy

mini and midi are byte-identical mirrors of mradermacher's community Q4_K_M quantizations. The WriteAmp app's catalog keeps mradermacher's URLs as the primary download path (the community attribution is preserved), and uses this repo as a cold-start fallback when the primary becomes unreachable or returns HTTP 404. See ADR-245 in the WriteAmp decision log for the full rationale.

The max tier is hosted here as the primary (no third-party mirror). It is also the source of truth for the max catalog slot.

License

All artifacts under this repo are distributed under the Apache License 2.0, consistent with their upstream base models (HuggingFaceTB/SmolLM2-135M, HuggingFaceTB/SmolLM2-360M, Qwen/Qwen3-0.6B-Base) and mradermacher's Q4_K_M quantizations of those bases.

Citation

@misc{writeamp_models_2026,
  title  = {WriteAmp on-device model catalog: SmolLM2 mirrors + Qwen3-0.6B Hinglish fine-tune},
  author = {DataDab LLP},
  year   = {2026},
  url    = {https://huggingface.co/datadab/writeamp-models}
}

Downloads last month: 62

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

4-bit