Instructions to use curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM with Transformers:

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

pipe = pipeline("text-generation", model="curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM

SGLang

How to use curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM 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 "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM with Docker Model Runner:
```
docker model run hf.co/curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM
```

Microsoft Phi-4 4-bit AWQ Quantized Model (GEMM)

This is a 4-bit AutoAWQ quantized version of Microsoft's Phi-4.
It is optimized for fast inference using vLLM with minimal loss in accuracy.

🚀 Model Details

Base Model: microsoft/phi-4
Quantization: 4-bit AWQ
Quantization Method: AutoAWQ (Activation-Aware Quantization)
Group Size: 128
AWQ Version: GEMM Optimized
Intended Use: Low VRAM inference on consumer GPUs
VRAM Requirements: ✅ 8GB+ (Recommended)
Compatibility: ✅ vLLM, Hugging Face Transformers (w/ AWQ support)

📌 How to Use in vLLM

You can load this model directly in vLLM for efficient inference:

vllm serve "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM"

Then, test it using cURL:

curl -X POST "http://localhost:8000/generate" \
    -H "Content-Type: application/json" \
    -d '{"prompt": "Explain quantum mechanics in simple terms.", "max_tokens": 100}'

📌 How to Use in Python (`transformers` + AWQ)

To use this model with Hugging Face Transformers:

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_path = "curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM"
model = AutoAWQForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

inputs = tokenizer("What is the meaning of life?", return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(output[0], skip_special_tokens=True))

📌 Quantization Details

This model was quantized using AutoAWQ with the following parameters:

Bits: 4-bit quantization
Zero-Point Quantization: Enabled (zero_point=True)
Group Size: 128 (q_group_size=128)
Quantization Version: GEMM
Method Used: AutoAWQ

📌 VRAM Requirements

Model Size	FP16 (No Quant)	AWQ 4-bit Quantized
Phi-4 14B	❌ Requires >20GB VRAM	✅ 8GB-12GB VRAM

AWQ significantly reduces VRAM requirements, making it possible to run 14B models on consumer GPUs. 🚀

📌 License & Credits

Base Model: Microsoft Phi-4
Quantized by: curiousmind147
License: Same as the base model (Microsoft)
Credits: This model is based on Microsoft's Phi-4 and was optimized using AutoAWQ.

📌 Acknowledgments

Special thanks to:

Microsoft for creating Phi-4.
Casper Hansen for developing AutoAWQ.
The vLLM team for making fast inference possible.

🚀 Enjoy Efficient Phi-4 Inference!

If you find this useful, give it a ⭐ on Hugging Face! 🎯

Downloads last month: 661

Safetensors

Model size

15B params

Tensor type

I32

BF16

Model tree for curiousmind147/microsoft-phi-4-AWQ-4bit-GEMM

Base model

microsoft/phi-4

Quantized

(149)

this model