Instructions to use stevenpr/chaty-qwen3.5-4b-design-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="stevenpr/chaty-qwen3.5-4b-design-GGUF",
	filename="chaty-qwen3.5-4b-design-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 stevenpr/chaty-qwen3.5-4b-design-GGUF 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 stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf stevenpr/chaty-qwen3.5-4b-design-GGUF: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 stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf stevenpr/chaty-qwen3.5-4b-design-GGUF: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 stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M

Use Docker

docker model run hf.co/stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stevenpr/chaty-qwen3.5-4b-design-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stevenpr/chaty-qwen3.5-4b-design-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M

Ollama
How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with Ollama:
```
ollama run hf.co/stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M
```

Unsloth Studio

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF 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 stevenpr/chaty-qwen3.5-4b-design-GGUF 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 stevenpr/chaty-qwen3.5-4b-design-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for stevenpr/chaty-qwen3.5-4b-design-GGUF to start chatting

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stevenpr/chaty-qwen3.5-4b-design-GGUF: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": "stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stevenpr/chaty-qwen3.5-4b-design-GGUF: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 stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf stevenpr/chaty-qwen3.5-4b-design-GGUF: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 "stevenpr/chaty-qwen3.5-4b-design-GGUF: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 stevenpr/chaty-qwen3.5-4b-design-GGUF with Docker Model Runner:
```
docker model run hf.co/stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M
```

Lemonade

How to use stevenpr/chaty-qwen3.5-4b-design-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stevenpr/chaty-qwen3.5-4b-design-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.chaty-qwen3.5-4b-design-GGUF-Q4_K_M

List all available models

lemonade list

Chaty · Qwen3.5-4B Design (GGUF)

A small, on-device model fine-tuned to give Chaty — a private, fully-local desktop chat app — stronger single-file web/HTML design on weak hardware, while self-identifying as Chaty and following Chaty's retrieval-grounding contract.

Base model: Qwen/Qwen3.5-4B (Apache-2.0)
Created by: Fangyuan Lin (author of Chaty)
Format: GGUF, Q4_K_M quant — runs in llama.cpp, LM Studio, or Chaty
Languages: English + 简体中文

What it's for

Chaty runs entirely on the user's own device (no cloud). This model is tuned so that weak-hardware users get better-looking, leaner web pages, faster — and so Chaty's assistant behaves consistently:

Web design — concise, self-contained single-file HTML pages (premium typography, dark/editorial styles), ~20–30% fewer tokens than the base ⇒ faster generation on weak hardware.
Identity — reliably self-identifies as Chaty (a fine-tuned Qwen3.5-4B running locally), created by Fangyuan Lin; uses no version number.
RAG grounding — when given numbered passages, cites with 【n】 and refuses ("not mentioned") when the answer is absent.

How it was made

LoRA fine-tune (Unsloth, bf16) of Qwen/Qwen3.5-4B, then exported to GGUF and quantized to Q4_K_M. Training data (≈760 examples):

Web design distilled from a local Qwen3.6-35B-A3B teacher (concise-but-complete pages, rendered & QC-filtered with a headless-Chrome / CDP probe).
RAG grounding contracts (【n】 citations + graceful refusals).
Identity distilled from the same 35B teacher under a Chaty persona (bilingual).

Evaluation (honest)

Held-out sets; base = Qwen3.5-4B, heuristic-scored (no LLM judge).

Dimension	base	this model
Self-identifies as Chaty	0%	94%
RAG 【n】 citation compliance	100%	100%
RAG refusal when answer absent	100%	100%
Design: clean render (0 JS errors + real content)	56%	59%
Design: self-contained single file	89%	97%
Avg tokens / page (↓ = faster on weak HW)	~6000	~4700

Trade-off: the gain is a more refined, leaner design style + consistent Chaty behavior; the cost is occasional content-fidelity slips on data-heavy interactive widgets (e.g. decimal-price formatting, complex JS logic). It is a 4B model specialized for Chaty's workflow, not a general chat assistant.

Run it

llama.cpp:

llama-cli -m chaty-qwen3.5-4b-design-Q4_K_M.gguf -p "Design a pricing page for a meditation app."

Or load the GGUF in LM Studio, or drop it into Chaty's models folder.

License

Apache-2.0, inherited from the base model Qwen/Qwen3.5-4B.

Downloads last month: 399

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for stevenpr/chaty-qwen3.5-4b-design-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(391)

this model