Instructions to use clawdiaonduty/clawdia-qwen3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use clawdiaonduty/clawdia-qwen3-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="clawdiaonduty/clawdia-qwen3-4b",
	filename="qwen3-4b-clawdia.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use clawdiaonduty/clawdia-qwen3-4b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf clawdiaonduty/clawdia-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clawdiaonduty/clawdia-qwen3-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf clawdiaonduty/clawdia-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clawdiaonduty/clawdia-qwen3-4b: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 clawdiaonduty/clawdia-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf clawdiaonduty/clawdia-qwen3-4b: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 clawdiaonduty/clawdia-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf clawdiaonduty/clawdia-qwen3-4b:Q4_K_M

Use Docker

docker model run hf.co/clawdiaonduty/clawdia-qwen3-4b:Q4_K_M

LM Studio
Jan

vLLM

How to use clawdiaonduty/clawdia-qwen3-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "clawdiaonduty/clawdia-qwen3-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "clawdiaonduty/clawdia-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/clawdiaonduty/clawdia-qwen3-4b:Q4_K_M

Ollama
How to use clawdiaonduty/clawdia-qwen3-4b with Ollama:
```
ollama run hf.co/clawdiaonduty/clawdia-qwen3-4b:Q4_K_M
```

Unsloth Studio

How to use clawdiaonduty/clawdia-qwen3-4b 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 clawdiaonduty/clawdia-qwen3-4b 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 clawdiaonduty/clawdia-qwen3-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for clawdiaonduty/clawdia-qwen3-4b to start chatting

How to use clawdiaonduty/clawdia-qwen3-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf clawdiaonduty/clawdia-qwen3-4b: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": "clawdiaonduty/clawdia-qwen3-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use clawdiaonduty/clawdia-qwen3-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf clawdiaonduty/clawdia-qwen3-4b: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 clawdiaonduty/clawdia-qwen3-4b:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use clawdiaonduty/clawdia-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/clawdiaonduty/clawdia-qwen3-4b:Q4_K_M
```

Lemonade

How to use clawdiaonduty/clawdia-qwen3-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull clawdiaonduty/clawdia-qwen3-4b:Q4_K_M

Run and chat with the model

lemonade run user.clawdia-qwen3-4b-Q4_K_M

List all available models

lemonade list

Clawdia-Qwen3-4B

LoRA fine-tune of Qwen/Qwen3-4B for on-device use inside Clawdia. Bigger sibling of the 1.7B build — same training data, better instruction-following, fewer hallucinations on Clawdia-specific UI questions.

This is the recommended local model for systems with 8+ GB RAM. The Q5_K_M GGUF is ~2.7 GB; pair it with Clawdia's bundled llama.cpp runtime.

For a smaller (1.2 GB) variant, see clawdiaonduty/clawdia-qwen3-1.7b.

Files

File	Format	Size	Use
`qwen3-4b-clawdia.Q5_K_M.gguf`	GGUF, Q5_K_M	2.7 GB	Recommended — best quality / speed trade-off
`qwen3-4b-clawdia.Q4_K_M.gguf`	GGUF, Q4_K_M	2.3 GB	Smaller, slightly worse
`qwen3-4b-clawdia.f16.gguf`	GGUF, f16	7.5 GB	Full precision (for further fine-tuning or reference)

How to use

Inside Clawdia (recommended)

Settings → Local Inference → pick Clawdia-Qwen3 4B Q5_K_M. Clawdia downloads to ~/.clawdia/local-inference/models/ and runs it via the bundled llama.cpp runtime.

llama.cpp directly

llama-completion \
  --model qwen3-4b-clawdia.Q5_K_M.gguf \
  --jinja \
  -sysf system_prompt.txt \
  -p "log $14.50 for lunch /no_think" \
  --temp 0.0 -n 280

Two critical flags:

--jinja: enables the embedded Qwen3 chat template (tool calls depend on this).
Append /no_think to user messages — Qwen3's base thinking mode wastes tokens before reaching tool calls.

What it does well

Probe	Output
`"who are you?"`	"Clawdia. macOS assistant. Runs on-device by default. I can send messages, schedule reminders, log expenses, take screenshots, run CLIs, and keep a memory wiki."
`"how do I switch to claude opus?"`	"Settings → Providers → Anthropic → paste API key → save. Then pick a Claude Opus model in the chat-header dropdown."
`"how do I enable iMessage?"`	Numbered steps for Full Disk Access + Automation + watch handle + restart.
`"where is my data stored?"`	"Everything lives at `~/.clawdia/`. The chat history, memory wiki, scheduled tasks, settings, and model downloads are there."
`"lunch was 30 for 2 of us and we split"`	`math(expression="30 / 2")` first, then logs the $15 share.
`"remind me on the 28th of every month to pay rent"`	`scheduled_task_create({"name":"Pay rent","schedule":{"every":1,"unit":"month","dayOfMonth":28,"atTime":"09:00"},"audience":"user","category":"Finance"})`
`"rm -rf my home directory"`	"Not running that — it would wipe your home folder. If you meant deleting a specific subfolder, point it out and I'll do that."

Training

Base: Qwen/Qwen3-4B
Adapter: LoRA rank 32, alpha 32, dropout 0.05 — applied to q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj on the top 16 transformer layers
Data: 1,662 hand-authored multi-turn dialogs across 25 categories (finance, memory, iMessage, Telegram/WhatsApp, scheduled tasks, pantry, proactive, todos/habits/journal, setup/safety, edge cases, indirect/proactive offers, goal-aware reasoning, math splits, packages/orders, web/news, MCP tools, memory CLI, Clawdia self-knowledge, Clawdia UI / don't-lie discipline)
Mask: train_on_responses_only — loss only on assistant tokens
Schedule: AdamW, lr 2e-4, cosine decay, 5% warmup, 4 epochs (~430 steps), effective batch 16, max_seq_length=6144
Hardware: 1× Modal H100, ~29 min wall-clock
Loss: averaged 0.40 (train), best eval 0.565 at epoch 1.92 (final eval climbed — slight overfit; use earlier checkpoint if needed)

Known rough edges

Tool-name drift in some finance/memory calls: occasionally emits finance_add_expense instead of canonical finance(action="add_expense"). Less frequent than the 1.7B variant but still happens. Targeted fix in next iteration.
Identity string drift: When asked "what model are you?" the 4B variant still answers "Clawdia-Qwen3-1.7B" — the training data was authored for the 1.7B build. Cosmetic.