Instructions to use bartowski/starcoder2-15b-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/starcoder2-15b-instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/starcoder2-15b-instruct-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/starcoder2-15b-instruct-GGUF", dtype="auto")

llama-cpp-python

How to use bartowski/starcoder2-15b-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/starcoder2-15b-instruct-GGUF",
	filename="starcoder2-15b-instruct-Q2_K.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 bartowski/starcoder2-15b-instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/starcoder2-15b-instruct-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 bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/starcoder2-15b-instruct-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 bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/starcoder2-15b-instruct-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 bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/starcoder2-15b-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/starcoder2-15b-instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/starcoder2-15b-instruct-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M

SGLang

How to use bartowski/starcoder2-15b-instruct-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 "bartowski/starcoder2-15b-instruct-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": "bartowski/starcoder2-15b-instruct-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 "bartowski/starcoder2-15b-instruct-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": "bartowski/starcoder2-15b-instruct-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use bartowski/starcoder2-15b-instruct-GGUF with Ollama:
```
ollama run hf.co/bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use bartowski/starcoder2-15b-instruct-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 bartowski/starcoder2-15b-instruct-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 bartowski/starcoder2-15b-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/starcoder2-15b-instruct-GGUF to start chatting

Docker Model Runner
How to use bartowski/starcoder2-15b-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/starcoder2-15b-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/starcoder2-15b-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.starcoder2-15b-instruct-GGUF-Q4_K_M

List all available models

lemonade list

Llamacpp Quantizations of starcoder2-15b-instruct

Using llama.cpp release b2354 for quantization.

Original model: https://huggingface.co/TechxGenus/starcoder2-15b-instruct

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Description
starcoder2-15b-instruct-Q8_0.gguf	Q8_0	16.96GB	Extremely high quality, generally unneeded but max available quant.
starcoder2-15b-instruct-Q6_K.gguf	Q6_K	13.10GB	Very high quality, near perfect, recommended.
starcoder2-15b-instruct-Q5_K_M.gguf	Q5_K_M	11.43GB	High quality, very usable.
starcoder2-15b-instruct-Q5_K_S.gguf	Q5_K_S	11.02GB	High quality, very usable.
starcoder2-15b-instruct-Q5_0.gguf	Q5_0	11.02GB	High quality, older format, generally not recommended.
starcoder2-15b-instruct-Q4_K_M.gguf	Q4_K_M	9.86GB	Good quality, similar to 4.25 bpw.
starcoder2-15b-instruct-Q4_K_S.gguf	Q4_K_S	9.25GB	Slightly lower quality with small space savings.
starcoder2-15b-instruct-Q4_0.gguf	Q4_0	9.06GB	Decent quality, older format, generally not recommended.
starcoder2-15b-instruct-Q3_K_L.gguf	Q3_K_L	8.96GB	Lower quality but usable, good for low RAM availability.
starcoder2-15b-instruct-Q3_K_M.gguf	Q3_K_M	8.10GB	Even lower quality.
starcoder2-15b-instruct-Q3_K_S.gguf	Q3_K_S	6.98GB	Low quality, not recommended.
starcoder2-15b-instruct-Q2_K.gguf	Q2_K	6.19GB	Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month: 331

GGUF

Model size

16B params

Architecture

starcoder2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant