Instructions to use ShayonSarker/StarCoder2-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShayonSarker/StarCoder2-3B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="ShayonSarker/StarCoder2-3B-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ShayonSarker/StarCoder2-3B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ShayonSarker/StarCoder2-3B-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 ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ShayonSarker/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 serve -hf ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ShayonSarker/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 ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ShayonSarker/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 ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ShayonSarker/StarCoder2-3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ShayonSarker/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": "ShayonSarker/StarCoder2-3B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M

SGLang

How to use ShayonSarker/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 "ShayonSarker/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": "ShayonSarker/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 "ShayonSarker/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": "ShayonSarker/StarCoder2-3B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ShayonSarker/StarCoder2-3B-GGUF with Ollama:
```
ollama run hf.co/ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use ShayonSarker/StarCoder2-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/ShayonSarker/StarCoder2-3B-GGUF:Q4_K_M
```

Lemonade

How to use ShayonSarker/StarCoder2-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ShayonSarker/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

Atomic Chat

StarCoder2-3B GGUF

Source model · HF release · Build hub

This release contains a validated Q4_K_M artifact for the StarCoder2-3B base model. The weights come from the established second-state/StarCoder2-3B-GGUF Q4_K_M conversion; no weight values were changed. The GGUF metadata was repaired to add the required tokenizer.ggml.pre=starcoder field, which removes llama.cpp's missing-pre-tokenizer warning.

Format status

File	Status	Purpose
`starcoder2-3b-Q4_K_M.gguf`	Published	Compact code model
`starcoder2-3b-F16.gguf`	Not published	Source checkpoint download exceeded the available transfer budget
`starcoder2-3b-Q8_0.gguf`	Not published	Same reason; it would have to be requantised from the source, not from Q4

The source checkpoint is 12.1 GB, so a fresh source conversion was not repeated here. The included build_gguf.py can build F16, Q8_0, and Q4_K_M from the pinned source when the download and disk requirements are available.

Verified code completions

Verbatim starcoder2-3b-Q4_K_M.gguf completions, --temp 0, 24 new tokens. The prompt is the def/for/SELECT line plus the already-given return or print(, and the model's text is reproduced as-is.

Prompt	Model completion
`def is_even(number):` `return`	`number % 2 == 0`
`def reverse_text(text):` `return`	`text[::-1]`
`def factorial(number):` `if number <= 1:` `return`	`1` `else:` `return number * factorial(number - 1)`
`def sum_list(numbers):` `return`	`sum(numbers)`
`def find_max(numbers):` `return`	`max(numbers)`
`for index, item in enumerate(items):` `print(`	`index, item)`

Python is clean. SQL is not, and it fails differently from DeepSeek-Coder: SELECT name FROM users WHERE active = drifts into a JavaScript then(result => ...) block, and SELECT COUNT(*) FROM orders WHERE total > emits 10000000000000000000000. StarCoder2-3B is a base model, so the trailing print(...) test calls and generated helper functions are trimmed above rather than presented as intended output.

Validation

WikiText-2 raw test evaluation, 8 chunks of 512 tokens:

Format	PPL
Q4_K_M, metadata repaired	11.7857 +/- 0.67032

A deterministic code-completion smoke test completed successfully:

def add(a, b):
    return a + b

Build

python -m pip install -r requirements-build.txt
python build_gguf.py --model-id bigcode/starcoder2-3b

The builder pins llama.cpp commit 6b790a9c291b5d7af3312bbf9f0c558aa023b13e and the upstream model revision. It does not upload or overwrite this repository.

License and provenance

BigCode OpenRAIL-M. See the upstream model card, the LICENSE notice, and the full license agreement linked there. The Q4_K_M weights are attributed to second-state/StarCoder2-3B-GGUF; this repository only repairs missing GGUF tokenizer metadata and adds documentation.

Downloads last month: 53

GGUF

Model size

3B params

Architecture

starcoder2

Hardware compatibility

4-bit

Model tree for ShayonSarker/StarCoder2-3B-GGUF

Base model

bigcode/starcoder2-3b

Quantized

(32)

this model