Instructions to use Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Ellbendls/Qwen-3-4b-Text_to_SQL-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 Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ellbendls/Qwen-3-4b-Text_to_SQL-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 Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ellbendls/Qwen-3-4b-Text_to_SQL-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 Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ellbendls/Qwen-3-4b-Text_to_SQL-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 Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ellbendls/Qwen-3-4b-Text_to_SQL-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": "Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M

Ollama
How to use Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF with Ollama:
```
ollama run hf.co/Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M
```

Unsloth Studio

How to use Ellbendls/Qwen-3-4b-Text_to_SQL-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 Ellbendls/Qwen-3-4b-Text_to_SQL-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 Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF to start chatting

Docker Model Runner
How to use Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF with Docker Model Runner:
```
docker model run hf.co/Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M
```

Lemonade

How to use Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ellbendls/Qwen-3-4b-Text_to_SQL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen-3-4b-Text_to_SQL-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Ellbendls commited on Sep 17, 2025

Commit

bb0e3e2

verified ·

1 Parent(s): fac762c

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -26

README.md CHANGED Viewed

@@ -101,32 +101,6 @@ print(out["choices"][0]["text"].strip())
 * Set temperature 0.1–0.3 for deterministic SQL.
 * Use a system prompt to anchor behavior.
-## Prompting tips (Text-to-SQL)
-Use clear instructions. Give schema if you have it. Ask for SQL only.
-**With schema**
-```
-You are a Text-to-SQL generator. Return only SQL.
-Schema:
-tables: employees(emp_id, name, dept_id, salary, hired_at)
-departments(dept_id, name)
-Task:
-Average salary by department for year 2024. Use ANSI SQL.
-```
-**Without schema**
-```
-You are a Text-to-SQL generator. Return only SQL.
-If schema missing, assume a minimal reasonable schema.
-Task:
-Top 5 products by revenue in Q2 2024. Use ANSI SQL.
-```
 ## Model details
 * **Base**. `Qwen/Qwen3-4B-Instruct-2507` (32k context, multilingual).

 * Set temperature 0.1–0.3 for deterministic SQL.
 * Use a system prompt to anchor behavior.
 ## Model details
 * **Base**. `Qwen/Qwen3-4B-Instruct-2507` (32k context, multilingual).