Instructions to use emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4 with Transformers:

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

pipe = pipeline("text-generation", model="emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4

SGLang

How to use emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4 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 "emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4" \
    --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": "emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4",
		"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 "emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4" \
        --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": "emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4 with Docker Model Runner:
```
docker model run hf.co/emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4
```

llama-3.2-3b-bitsandbytes-4bit-nf4

This repository contains a quantized model artifact produced in the graduation project.

Model Details

Technique: BitsAndBytes
Quantization: NF4 (4-bit)
Base model: meta-llama/Llama-3.2-3B-Instruct
Export date: 2026-03-24

Benchmark Summary

Metric	Original	Quantized
Model size (GB)	5.98	2.05
Avg inference (sec)	29.59	3.83
Tokens/sec	3.38	26.13
Perplexity	41.4043	37.4797

Comparison Highlights

Speedup: N/Ax
Memory reduction: N/A%
Disk/model size reduction: N/A%

Benchmark Notes

Numbers below are copied from local benchmark_results JSON in this project.

Local Source

Quantized folder: Advanced-Techniques/MixedPrecision/quantized/4bit-nf4
Benchmark JSON: Advanced-Techniques/MixedPrecision/benchmark_results/bitsandbytes_benchmark.json

Usage

Use the model with the library and runtime that match the quantization technique in this repo.

Limitations

This model card is auto-generated from project files.
You should validate quality, safety, and license compatibility before public release.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for emreyigitozturk/llama-3.2-3b-bitsandbytes-4bit-nf4

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(2017)

this model