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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Gabbio/driptips-concierge-qwen3-4b 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 Gabbio/driptips-concierge-qwen3-4b:Q8_0
# Run inference directly in the terminal:
llama cli -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0
# Run inference directly in the terminal:
llama cli -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0

Use Docker

docker model run hf.co/Gabbio/driptips-concierge-qwen3-4b:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use Gabbio/driptips-concierge-qwen3-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gabbio/driptips-concierge-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": "Gabbio/driptips-concierge-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gabbio/driptips-concierge-qwen3-4b:Q8_0

Ollama
How to use Gabbio/driptips-concierge-qwen3-4b with Ollama:
```
ollama run hf.co/Gabbio/driptips-concierge-qwen3-4b:Q8_0
```
Unsloth Desktop

How to use Gabbio/driptips-concierge-qwen3-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0

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": "Gabbio/driptips-concierge-qwen3-4b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Gabbio/driptips-concierge-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/Gabbio/driptips-concierge-qwen3-4b:Q8_0
```

Lemonade

How to use Gabbio/driptips-concierge-qwen3-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gabbio/driptips-concierge-qwen3-4b:Q8_0

Run and chat with the model

lemonade run user.driptips-concierge-qwen3-4b-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Gabbio/driptips-concierge-qwen3-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0

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 Gabbio/driptips-concierge-qwen3-4b:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Gabbio/driptips-concierge-qwen3-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gabbio/driptips-concierge-qwen3-4b:Q8_0

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 "Gabbio/driptips-concierge-qwen3-4b:Q8_0" \
  --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"

driptips-concierge (Qwen3-4B, v5)

The trip-planning model of driptips, a team project for the Ostrovok O! Hackathon 2026, track «О!дин запрос». Code: https://github.com/ostrovok-hackathon-2026/driptips

It is Qwen/Qwen3-4B-Instruct-2507 fine-tuned with LoRA (r=16, all linear layers) and merged. It does two narrow jobs:

a guest's phrase in Russian → a JSON trip plan (plan_trip): destination, dates, guests and children's ages, budget per night or per trip, must-have and nice-to-have hotel features, trip type, weather and sea wishes, visa, food, questions;
an answer about a destination strictly from the provided reference (weather, visa, prices, flight time), without inventing numbers.

The application never shows the model's free text as facts: dates, budget and the reply to the guest are computed by code from a knowledge base, and every answer is checked against it.

Results (v5)

Test	Score
Independent test, 60 hand-written phrases: correct final search	95.0%
Same test: fully correct plan	76.7%
Template phrases: valid JSON / correct search	99.8% / 95.0%
Paraphrased phrases: valid JSON / correct search	99.5% / 72.4%
Destination questions: no invented numbers	100%

Use

Built for llama.cpp's OpenAI-compatible server (llama-server) on CPU; a GGUF version is produced from this repository. Training data, prompts and evaluation are in the GitHub repository (training/, docs/own-model.md).

License: Apache 2.0, same as the base model.

Downloads last month: 60

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Gabbio/driptips-concierge-qwen3-4b

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5887)

this model

Adapters

1 model