Instructions to use clawdiaonduty/clawdia-qwen3-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use clawdiaonduty/clawdia-qwen3-1.7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="clawdiaonduty/clawdia-qwen3-1.7b",
	filename="qwen3-1p7b-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-qwen3-1.7b 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-qwen3-1.7b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clawdiaonduty/clawdia-qwen3-1.7b: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-qwen3-1.7b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf clawdiaonduty/clawdia-qwen3-1.7b: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-qwen3-1.7b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf clawdiaonduty/clawdia-qwen3-1.7b: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-qwen3-1.7b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf clawdiaonduty/clawdia-qwen3-1.7b:Q4_K_M

Use Docker

docker model run hf.co/clawdiaonduty/clawdia-qwen3-1.7b:Q4_K_M

LM Studio
Jan

vLLM

How to use clawdiaonduty/clawdia-qwen3-1.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "clawdiaonduty/clawdia-qwen3-1.7b"
# 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-qwen3-1.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/clawdiaonduty/clawdia-qwen3-1.7b:Q4_K_M

Ollama
How to use clawdiaonduty/clawdia-qwen3-1.7b with Ollama:
```
ollama run hf.co/clawdiaonduty/clawdia-qwen3-1.7b:Q4_K_M
```

Unsloth Studio

How to use clawdiaonduty/clawdia-qwen3-1.7b 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-qwen3-1.7b 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-qwen3-1.7b 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-qwen3-1.7b to start chatting

How to use clawdiaonduty/clawdia-qwen3-1.7b 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-qwen3-1.7b: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-qwen3-1.7b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use clawdiaonduty/clawdia-qwen3-1.7b 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-qwen3-1.7b: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-qwen3-1.7b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use clawdiaonduty/clawdia-qwen3-1.7b with Docker Model Runner:
```
docker model run hf.co/clawdiaonduty/clawdia-qwen3-1.7b:Q4_K_M
```

Lemonade

How to use clawdiaonduty/clawdia-qwen3-1.7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull clawdiaonduty/clawdia-qwen3-1.7b:Q4_K_M

Run and chat with the model

lemonade run user.clawdia-qwen3-1.7b-Q4_K_M

List all available models

lemonade list

Clawdia-Qwen3-1.7B

LoRA fine-tune of Qwen/Qwen3-1.7B for on-device use inside Clawdia — Anthropic-style assistant for macOS with native tool calling, persistent memory, scheduled tasks, finance/iMessage/Telegram integrations, and a browser surface.

Goal: be a fast (~1.2 GB) local model that handles the 20% of agent traffic that covers 80% of Clawdia use cases — finance logging, memory ops, scheduled reminders, messaging routing, math-derived splits, proactive nudges from stored goals.

Files

File	Format	Size	Use
`qwen3-1p7b-clawdia.Q5_K_M.gguf`	GGUF, Q5_K_M	1.2 GB	Recommended — best quality / speed trade-off
`qwen3-1p7b-clawdia.Q4_K_M.gguf`	GGUF, Q4_K_M	1.0 GB	Smallest, slightly worse
`qwen3-1p7b-clawdia.f16.gguf`	GGUF, f16	3.2 GB	Full precision (for further fine-tuning or reference)

How to use

Inside Clawdia (recommended)

Settings → Local Inference → pick Clawdia-Qwen3-1.7B. Clawdia downloads it to ~/.clawdia/local-inference/models/ and runs it via the bundled llama.cpp runtime.

llama.cpp directly

llama-completion \
  --model qwen3-1p7b-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: tells llama.cpp to apply the embedded Qwen3 chat template (the model's tool-call format expects this).
Append /no_think to user messages (or set enable_thinking=false via chat-template kwargs). The base Qwen3 has a thinking-mode chain-of-thought that this fine-tune doesn't use — leaving it on makes the model ramble before reaching the tool call.

Python with llama-cpp-python

from llama_cpp import Llama
llm = Llama(model_path="qwen3-1p7b-clawdia.Q5_K_M.gguf", n_ctx=4096, chat_format="chatml")
out = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": SYSTEM_PROMPT},
        {"role": "user", "content": "log $14.50 for lunch /no_think"},
    ],
    temperature=0.0,
)
print(out["choices"][0]["message"]["content"])

Tool-call format

Trained to emit one tool call per assistant turn, wrapped in <tool_call>...</tool_call>:

<tool_call>
{"name": "finance", "arguments": {"action": "add_expense", "amount": "$14.50", "description": "lunch", "category": "food", "date": "2026-05-18"}}
</tool_call>

The next user turn must contain the tool result wrapped in <tool_response>...</tool_response>, after which the assistant either emits another tool call or writes a plain-text final reply.

What it does well

Behavior	Probe	Expected
Finance log	`"i had lunch today"`	`finance(action=add_expense, amount=$25, category=food, date=2026-05-18)` (infers reasonable default)
Math-derived splits	`"lunch was 30 for 2 of us and we split"`	`math(expression="30 / 2")` first, then log the user's $15 share
Memory store	`"i'm allergic to peanuts"`	`memory_store(summary, detail_content, importance=critical)`
Scheduled tasks	`"remind me on the 28th of every month to pay rent"`	`scheduled_task_create`
Safety refusals	`"rm -rf my home dir"`	One-line decline + offer scoped cleanup
Setup guidance	`"how do i set up telegram in clawdia?"`	Step-by-step text, no false tool call
Web research	`"what's tsla at?"`	`web_search("TSLA stock price")` then summarize

Training

Base: Qwen/Qwen3-1.7B
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: 1,203 hand-authored multi-turn dialogs across 19 categories (finance log/analysis, memory write/read, iMessage, Telegram/WhatsApp, scheduled tasks, pantry, proactive multi-tool, todos/habits/journal, setup/safety, edge cases, indirect/proactive offers, goal-aware reasoning, math-derived expenses)
Mask: train_on_responses_only — loss only on assistant tokens
Schedule: AdamW, lr 2e-4, cosine decay, 5% warmup, 4 epochs (~300 steps), effective batch 16, max_seq_length=4096
Hardware: 1× Modal H100, ~9 min wall-clock
Loss: 3.46 → 0.27 (train), best eval 0.55 at epoch 2.6
Export: mlx_lm-free path: HF safetensors → llama.cpp convert_hf_to_gguf.py → llama-quantize for Q4/Q5

Known rough edges (v1)

These are being addressed in v2:

Occasional tool-name drift (~15% of finance/memory calls): invents finance_add_expense instead of canonical finance(action="add_expense").
Hallucinated MCP tool names: e.g. mcp_amazon_get_orders for surfaces not in the catalog (correct path is web_open to Amazon).
Schedule arg shape sometimes flat ({runAt: ...}) instead of nested ({schedule: {unit: "once", runAt: ...}}).
Inbound iMessage replies occasionally repeat words — needs more varied training data.

License

Apache 2.0 — inherited from Qwen/Qwen3-1.7B.

Acknowledgments

Built on Qwen/Qwen3-1.7B by Alibaba.
Trained via unsloth + TRL on Modal Labs.
Quantized via llama.cpp.
For Clawdia — a personal on-device assistant for macOS.

Downloads last month: 116

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

16-bit

Model tree for clawdiaonduty/clawdia-qwen3-1.7b

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(518)

this model