Instructions to use pytorch/Phi-4-mini-instruct-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pytorch/Phi-4-mini-instruct-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="pytorch/Phi-4-mini-instruct-INT4", 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("pytorch/Phi-4-mini-instruct-INT4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("pytorch/Phi-4-mini-instruct-INT4", 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 Settings

vLLM

How to use pytorch/Phi-4-mini-instruct-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pytorch/Phi-4-mini-instruct-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pytorch/Phi-4-mini-instruct-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pytorch/Phi-4-mini-instruct-INT4

SGLang

How to use pytorch/Phi-4-mini-instruct-INT4 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 "pytorch/Phi-4-mini-instruct-INT4" \
    --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": "pytorch/Phi-4-mini-instruct-INT4",
		"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 "pytorch/Phi-4-mini-instruct-INT4" \
        --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": "pytorch/Phi-4-mini-instruct-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pytorch/Phi-4-mini-instruct-INT4 with Docker Model Runner:
```
docker model run hf.co/pytorch/Phi-4-mini-instruct-INT4
```

Update README.md

by supriyar - opened May 2, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-6

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -17,11 +17,11 @@ base_model:
 pipeline_tag: text-generation
 ---
-[Phi4-mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) model quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) int4 weight only quantization, by PyTorch team.
 # Quantization Recipe
-First need to install the required packages:
 ```
 pip install git+https://github.com/huggingface/transformers@main
 pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
@@ -29,7 +29,7 @@ pip install torch
 pip install accelerate
 ```
-We used following code to get the quantized model:
 ```
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
@@ -144,7 +144,6 @@ lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-int4wo-hq
 # Peak Memory Usage
-We can use the following code to get a sense of peak memory usage during inference:
 ## Results
@@ -155,6 +154,7 @@ We can use the following code to get a sense of peak memory usage during inferen
 ## Benchmark Peak Memory
 ```
 import torch
@@ -198,8 +198,8 @@ print(f"Peak Memory Usage: {mem:.02f} GB")
 # Model Performance
-Our int4wo is only optimized for batch size 1, so we'll see slowdown in larger batch sizes, we expect this to be used in local server deployment for single or a few users
-and decode tokens per second will be more important than time to first token.
 ## Results (A100 machine)

 pipeline_tag: text-generation
 ---
+[Phi4-mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) int4 weight only quantization, by PyTorch team. Use it directly or serve using [vLLM](https://docs.vllm.ai/en/latest/). Get 67% VRAM reduction and 12-20% speedup on A100 GPUs.
 # Quantization Recipe
+Install the required packages:
 ```
 pip install git+https://github.com/huggingface/transformers@main
 pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
 pip install accelerate
 ```
+Use the following code to get the quantized model:
 ```
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
 # Peak Memory Usage
 ## Results
 ## Benchmark Peak Memory
+We can use the following code to get a sense of peak memory usage during inference:
 ```
 import torch
 # Model Performance
+Our int4wo is only optimized for batch size 1, so expect some slowdown with larger batch sizes, we expect this to be used in local server deployment for single or a few users
+where the decode tokens per second will matters more than the time to first token.
 ## Results (A100 machine)