Instructions to use agentlans/Qwen3-4B-multilingual-sft-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use agentlans/Qwen3-4B-multilingual-sft-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="agentlans/Qwen3-4B-multilingual-sft-GGUF",
	filename="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 agentlans/Qwen3-4B-multilingual-sft-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf agentlans/Qwen3-4B-multilingual-sft-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 agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf agentlans/Qwen3-4B-multilingual-sft-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 agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M

Use Docker

docker model run hf.co/agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use agentlans/Qwen3-4B-multilingual-sft-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agentlans/Qwen3-4B-multilingual-sft-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": "agentlans/Qwen3-4B-multilingual-sft-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M

Ollama
How to use agentlans/Qwen3-4B-multilingual-sft-GGUF with Ollama:
```
ollama run hf.co/agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M
```

Unsloth Studio

How to use agentlans/Qwen3-4B-multilingual-sft-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 agentlans/Qwen3-4B-multilingual-sft-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 agentlans/Qwen3-4B-multilingual-sft-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for agentlans/Qwen3-4B-multilingual-sft-GGUF to start chatting

Docker Model Runner
How to use agentlans/Qwen3-4B-multilingual-sft-GGUF with Docker Model Runner:
```
docker model run hf.co/agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M
```

Lemonade

How to use agentlans/Qwen3-4B-multilingual-sft-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agentlans/Qwen3-4B-multilingual-sft-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-multilingual-sft-GGUF-Q4_K_M

List all available models

lemonade list

Qwen 3 4B Multilingual Quantized Models

This repo contains quantized versions of the agentlans/Qwen3-4B-multilingual-sft model, optimized for efficient local use with llama.cpp.

The models were quantized using an unofficial Docker image and calibrated on the first 100 rows of the LinguaNova dataset to maintain strong multilingual performance.

These quantized models share the same strengths and limitations as the original Qwen 3 4B multilingual model. They offer a lighter, faster alternative for inference with minor trade-offs in precision.

Downloads last month: 21

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for agentlans/Qwen3-4B-multilingual-sft-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

agentlans/Qwen3-4B-multilingual-sft

Quantized

(1)

this model

agentlans
/

Qwen3-4B-multilingual-sft-GGUF

Qwen 3 4B Multilingual Quantized Models

Model tree for agentlans/Qwen3-4B-multilingual-sft-GGUF

Dataset used to train agentlans/Qwen3-4B-multilingual-sft-GGUF