Instructions to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16")
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 RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16

SGLang

How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 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 "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16" \
    --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": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",
		"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 "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16" \
        --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": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16
```

Model Size

by bardia79mhd - opened Dec 12, 2025

Discussion

bardia79mhd

Dec 12, 2025

Hello,

The model's size on the card indicates 3B. Can you please confirm if this is correct?

Thanks!

alexmarques

Red Hat AI org Dec 12, 2025

Hello, it seems HF doesn't understand the weight packing. The embeddings and lm_head are left a BF16 and account for ~1B parameters. The other ~7B parameters are packed into INT32 tensors (4 8-bit parameters per value), so the HF counts them as ~2B parameters.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment