Instructions to use 08210821iy/Qwen3-4B-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 08210821iy/Qwen3-4B-Coder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="08210821iy/Qwen3-4B-Coder",
	filename="model-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use 08210821iy/Qwen3-4B-Coder with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 08210821iy/Qwen3-4B-Coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 08210821iy/Qwen3-4B-Coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 08210821iy/Qwen3-4B-Coder:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 08210821iy/Qwen3-4B-Coder: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 08210821iy/Qwen3-4B-Coder:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 08210821iy/Qwen3-4B-Coder: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 08210821iy/Qwen3-4B-Coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 08210821iy/Qwen3-4B-Coder:Q4_K_M

Use Docker

docker model run hf.co/08210821iy/Qwen3-4B-Coder:Q4_K_M

LM Studio
Jan

vLLM

How to use 08210821iy/Qwen3-4B-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "08210821iy/Qwen3-4B-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "08210821iy/Qwen3-4B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/08210821iy/Qwen3-4B-Coder:Q4_K_M

Ollama
How to use 08210821iy/Qwen3-4B-Coder with Ollama:
```
ollama run hf.co/08210821iy/Qwen3-4B-Coder:Q4_K_M
```

Unsloth Studio new

How to use 08210821iy/Qwen3-4B-Coder 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 08210821iy/Qwen3-4B-Coder 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 08210821iy/Qwen3-4B-Coder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 08210821iy/Qwen3-4B-Coder to start chatting

Pi new

How to use 08210821iy/Qwen3-4B-Coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf 08210821iy/Qwen3-4B-Coder: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": "08210821iy/Qwen3-4B-Coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 08210821iy/Qwen3-4B-Coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf 08210821iy/Qwen3-4B-Coder: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 08210821iy/Qwen3-4B-Coder:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use 08210821iy/Qwen3-4B-Coder with Docker Model Runner:
```
docker model run hf.co/08210821iy/Qwen3-4B-Coder:Q4_K_M
```

Lemonade

How to use 08210821iy/Qwen3-4B-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 08210821iy/Qwen3-4B-Coder:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-Coder-Q4_K_M

List all available models

lemonade list

Qwen3-4B-Coder

A fine-tuned Qwen3-4B model specialized for Python code generation, trained by an elementary school student on an RTX 4060 Laptop GPU (8 GB VRAM).

Qwen3-4Bをベースに、Pythonコード生成に特化してファインチューニングしたモデルです。小学生がRTX 4060 Laptop GPU (VRAM 8GB) で学習しました。

Benchmark Results

MBPP-sanitized (Practical Python Tasks)

Model	MBPP pass@1	Condition
Qwen3-4B-Coder (this model)	69.3% (178/257)	Q4_K_M, temperature=0.0
Qwen3-4B (official)	62.0%	FP16, EvalPlus

+7.3 points improvement on practical coding tasks.

HumanEval (Algorithmic Tasks)

Model	HumanEval pass@1	Condition
Qwen3-4B-Coder (this model)	47.6% (78/164)	Q4_K_M, temperature=0.0
Qwen3-4B (official)	65.6%	FP16, EvalPlus

Inference Speed

Benchmark	Qwen3-4B-Coder	Qwen3-4B (Q4_K_M)	Speed Ratio
HumanEval (164 tasks)	793s	3623s	4.6x faster
MBPP (257 tasks)	1274s	-	-

Syntax error rate on HumanEval: 0% (164/164)

Key Findings

This model demonstrates that SFT for code-only output has two major benefits:

Practical code generation ability improved (MBPP +7.3 points)
Inference speed improved 4.6x by eliminating think blocks and explanations

Training Details

Parameter	Value
Base Model	Qwen/Qwen3-4B
Method	SFT with LoRA (r=16, alpha=32)
Dataset	PersonalAILab/AFM-CodeAgent-SFT-Dataset
Training Samples	8,869 (filtered to 512 tokens)
Epochs	3
Final Loss	0.72
MAX_SEQ	512
GPU	NVIDIA RTX 4060 Laptop (8 GB VRAM)
Training Time	~5.5 hours
Quantization	Q4_K_M (~2.4 GB)

Features

Code-only output without extra explanations
4.6x faster inference than base model
Supports English and Japanese prompts
Optimized for agent pipelines
Syntax error rate 0% on HumanEval

AI Code Agent (CLI Tool)

An interactive CLI tool that uses this model to generate, execute, and auto-fix Python code.

git clone https://github.com/jiexiang018-tech/ai-python-agent.git
cd ai-python-agent
pip install -r requirements.txt
python setup.py
python agent.py

Downloads last month: 48

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for 08210821iy/Qwen3-4B-Coder

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(218)

this model