Instructions to use pytorch/Phi-4-mini-instruct-INT8-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pytorch/Phi-4-mini-instruct-INT8-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-INT8-INT4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pytorch/Phi-4-mini-instruct-INT8-INT4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("pytorch/Phi-4-mini-instruct-INT8-INT4", trust_remote_code=True, device_map="auto")
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=256)
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-INT8-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-INT8-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-INT8-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pytorch/Phi-4-mini-instruct-INT8-INT4

SGLang

How to use pytorch/Phi-4-mini-instruct-INT8-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-INT8-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-INT8-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-INT8-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-INT8-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pytorch/Phi-4-mini-instruct-INT8-INT4 with Docker Model Runner:
```
docker model run hf.co/pytorch/Phi-4-mini-instruct-INT8-INT4
```

jerryzh168 commited on May 3, 2025

Commit

fb71c2a

verified ·

1 Parent(s): 55e2bb7

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ On iPhone 15 Pro, the model runs at 17.3 tokens/sec and uses 3206 Mb of memory.
 # 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
 ```
@@ -39,7 +39,7 @@ pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/c
 ## Untie Embedding Weights
 Before quantization, since we need quantize input embedding and unembedding (lm_head) layer which are tied, but we want to quantize them separately, we first need to untie the model:
-```
 from transformers import (
   AutoModelForCausalLM,
   AutoProcessor,
@@ -73,7 +73,7 @@ tokenizer.push_to_hub(save_to)
 We used following code to get the quantized model:
-```
 from transformers import (
   AutoModelForCausalLM,
   AutoProcessor,
@@ -156,12 +156,12 @@ We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-h
 Need to install lm-eval from source: https://github.com/EleutherAI/lm-evaluation-harness#install
 ## baseline
-```
 lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size 64
 ```
 ## int8 dynamic activation and int4 weight quantization (8da4w)
-```
 lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-8da4w --tasks hellaswag --device cuda:0 --batch_size 64
 ```
@@ -195,13 +195,13 @@ Once ExecuTorch is [set-up](https://pytorch.org/executorch/main/getting-started.
 We first convert the [quantized checkpoint](https://huggingface.co/pytorch/Phi-4-mini-instruct-8da4w/blob/main/pytorch_model.bin) to one ExecuTorch's LLM export script expects by renaming some of the checkpoint keys.
 The following script does this for you.  We have uploaded the converted checkpoint [phi4-mini-8da4w-converted.bin](https://huggingface.co/pytorch/Phi-4-mini-instruct-8da4w/blob/main/phi4-mini-8da4w-converted.bin) for convenience.
-```
 python -m executorch.examples.models.phi_4_mini.convert_weights pytorch_model.bin phi4-mini-8da4w-converted.bin
 ```
 Once the checkpoint is converted, we can export to ExecuTorch's PTE format with the XNNPACK delegate.
-```
 PARAMS="executorch/examples/models/phi_4_mini/config.json"
 python -m executorch.examples.models.llama.export_llama \
   --model "phi_4_mini" \

 # Quantization Recipe
 First need to install the required packages:
+```Shell
 pip install git+https://github.com/huggingface/transformers@main
 pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
 ```
 ## Untie Embedding Weights
 Before quantization, since we need quantize input embedding and unembedding (lm_head) layer which are tied, but we want to quantize them separately, we first need to untie the model:
+```Py
 from transformers import (
   AutoModelForCausalLM,
   AutoProcessor,
 We used following code to get the quantized model:
+```Py
 from transformers import (
   AutoModelForCausalLM,
   AutoProcessor,
 Need to install lm-eval from source: https://github.com/EleutherAI/lm-evaluation-harness#install
 ## baseline
+```Shell
 lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size 64
 ```
 ## int8 dynamic activation and int4 weight quantization (8da4w)
+```Shell
 lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-8da4w --tasks hellaswag --device cuda:0 --batch_size 64
 ```
 We first convert the [quantized checkpoint](https://huggingface.co/pytorch/Phi-4-mini-instruct-8da4w/blob/main/pytorch_model.bin) to one ExecuTorch's LLM export script expects by renaming some of the checkpoint keys.
 The following script does this for you.  We have uploaded the converted checkpoint [phi4-mini-8da4w-converted.bin](https://huggingface.co/pytorch/Phi-4-mini-instruct-8da4w/blob/main/phi4-mini-8da4w-converted.bin) for convenience.
+```Shell
 python -m executorch.examples.models.phi_4_mini.convert_weights pytorch_model.bin phi4-mini-8da4w-converted.bin
 ```
 Once the checkpoint is converted, we can export to ExecuTorch's PTE format with the XNNPACK delegate.
+```Shell
 PARAMS="executorch/examples/models/phi_4_mini/config.json"
 python -m executorch.examples.models.llama.export_llama \
   --model "phi_4_mini" \