Instructions to use ysn-rfd/starcoder2-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ysn-rfd/starcoder2-3b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ysn-rfd/starcoder2-3b-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ysn-rfd/starcoder2-3b-GGUF", dtype="auto")

llama-cpp-python

How to use ysn-rfd/starcoder2-3b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ysn-rfd/starcoder2-3b-GGUF",
	filename="starcoder2-3b-q4_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ysn-rfd/starcoder2-3b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ysn-rfd/starcoder2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ysn-rfd/starcoder2-3b-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 ysn-rfd/starcoder2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ysn-rfd/starcoder2-3b-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 ysn-rfd/starcoder2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ysn-rfd/starcoder2-3b-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 ysn-rfd/starcoder2-3b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ysn-rfd/starcoder2-3b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ysn-rfd/starcoder2-3b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ysn-rfd/starcoder2-3b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ysn-rfd/starcoder2-3b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ysn-rfd/starcoder2-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ysn-rfd/starcoder2-3b-GGUF:Q4_K_M

SGLang

How to use ysn-rfd/starcoder2-3b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ysn-rfd/starcoder2-3b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ysn-rfd/starcoder2-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ysn-rfd/starcoder2-3b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ysn-rfd/starcoder2-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ysn-rfd/starcoder2-3b-GGUF with Ollama:
```
ollama run hf.co/ysn-rfd/starcoder2-3b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use ysn-rfd/starcoder2-3b-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 ysn-rfd/starcoder2-3b-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 ysn-rfd/starcoder2-3b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ysn-rfd/starcoder2-3b-GGUF to start chatting

Docker Model Runner
How to use ysn-rfd/starcoder2-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/ysn-rfd/starcoder2-3b-GGUF:Q4_K_M
```

Lemonade

How to use ysn-rfd/starcoder2-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ysn-rfd/starcoder2-3b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.starcoder2-3b-GGUF-Q4_K_M

List all available models

lemonade list

ysn-rfd/starcoder2-3b-GGUF

This model was converted to GGUF format from bigcode/starcoder2-3b using llama.cpp via the ggml.ai's all-gguf-same-where space. Refer to the original model card for more details on the model.

✅ Quantized Models Download List

🔍 Recommended Quantizations

✨ General CPU Use: Q4_K_M (Best balance of speed/quality)
📱 ARM Devices: Q4_0 (Optimized for ARM CPUs)
🏆 Maximum Quality: Q8_0 (Near-original quality)

📦 Full Quantization Options

🚀 Download	🔢 Type	📝 Notes
Download		Basic quantization
Download		Small size
Download		Balanced quality
Download		Better quality
Download		Fast on ARM
Download		Fast, recommended
Download	⭐	Best balance
Download		Good quality
Download		Balanced
Download		High quality
Download	🏆	Very good quality
Download	⚡	Fast, best quality
Download		Maximum accuracy

💡 Tip: Use F16 for maximum precision when quality is critical

🚀 Applications and Tools for Locally Quantized LLMs

🖥️ Desktop Applications

Application	Description	Download Link
Llama.cpp	A fast and efficient inference engine for GGUF models.	GitHub Repository
Ollama	A streamlined solution for running LLMs locally.	Website
AnythingLLM	An AI-powered knowledge management tool.	GitHub Repository
Open WebUI	A user-friendly web interface for running local LLMs.	GitHub Repository
GPT4All	A user-friendly desktop application supporting various LLMs, compatible with GGUF models.	GitHub Repository
LM Studio	A desktop application designed to run and manage local LLMs, supporting GGUF format.	Website
GPT4All Chat	A chat application compatible with GGUF models for local, offline interactions.	GitHub Repository

📱 Mobile Applications

Application	Description	Download Link
ChatterUI	A simple and lightweight LLM app for mobile devices.	GitHub Repository
Maid	Mobile Artificial Intelligence Distribution for running AI models on mobile devices.	GitHub Repository
PocketPal AI	A mobile AI assistant powered by local models.	GitHub Repository
Layla	A flexible platform for running various AI models on mobile devices.	Website

🎨 Image Generation Applications

Application	Description	Download Link
Stable Diffusion	An open-source AI model for generating images from text.	GitHub Repository
Stable Diffusion WebUI	A web application providing access to Stable Diffusion models via a browser interface.	GitHub Repository
Local Dream	Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference.	GitHub Repository
Stable-Diffusion-Android (SDAI)	An open-source AI art application for Android devices, enabling digital art creation.	GitHub Repository

Downloads last month: 65

GGUF

Model size

3B params

Architecture

starcoder2

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for ysn-rfd/starcoder2-3b-GGUF

Base model

bigcode/starcoder2-3b

Quantized

(26)

this model

Dataset used to train ysn-rfd/starcoder2-3b-GGUF

Collection including ysn-rfd/starcoder2-3b-GGUF

Best Models

Collection

11 items • Updated Apr 4, 2025

Evaluation results

pass@1 on CruxEval-I
self-reported

32.700
pass@1 on DS-1000
self-reported

25.000
accuracy on GSM8K (PAL)
self-reported

27.700
pass@1 on HumanEval+
self-reported

27.400
pass@1 on HumanEval
self-reported

31.700
edit-smiliarity on RepoBench-v1.1
self-reported

71.190