Instructions to use zkvesl/Llama-3.2-3B-Instruct-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zkvesl/Llama-3.2-3B-Instruct-int8 with Transformers:

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

pipe = pipeline("text-generation", model="zkvesl/Llama-3.2-3B-Instruct-int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zkvesl/Llama-3.2-3B-Instruct-int8")
model = AutoModelForCausalLM.from_pretrained("zkvesl/Llama-3.2-3B-Instruct-int8")
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 zkvesl/Llama-3.2-3B-Instruct-int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zkvesl/Llama-3.2-3B-Instruct-int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zkvesl/Llama-3.2-3B-Instruct-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zkvesl/Llama-3.2-3B-Instruct-int8

SGLang

How to use zkvesl/Llama-3.2-3B-Instruct-int8 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 "zkvesl/Llama-3.2-3B-Instruct-int8" \
    --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": "zkvesl/Llama-3.2-3B-Instruct-int8",
		"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 "zkvesl/Llama-3.2-3B-Instruct-int8" \
        --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": "zkvesl/Llama-3.2-3B-Instruct-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zkvesl/Llama-3.2-3B-Instruct-int8 with Docker Model Runner:
```
docker model run hf.co/zkvesl/Llama-3.2-3B-Instruct-int8
```

Llama-3.2-3B-Instruct-INT8

INT8 quantized version of Llama-3.2-3B-Instruct, produced for Nockchain using the Pearl quantization methodology.

Quantization Details

Method: W8A8 (weight-only INT8 + dynamic activation INT8)
Weights: Symmetric per-channel quantization
Activations: Symmetric per-token dynamic quantization
lm_head and embeddings remain in FP16/BF16

This checkpoint follows the compressed-tensors W8A8 scheme and is compatible with vLLM and Nockchain serving pipeline.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zkvesl/Llama-3.2-3B-Instruct-int8")
model = AutoModelForCausalLM.from_pretrained(
    "zkvesl/Llama-3.2-3B-Instruct-int8",
    torch_dtype="auto",
    device_map="auto"
)

inputs = tokenizer("Hello, my name is", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))

Pearl Quantization Methodology

This model was quantized using the Pearl methodology, which ensures bit-exact integer matrix multiplication for inference while maintaining accuracy through GPTQ calibration and SmoothQuant optimization.

References

Downloads last month: 41

Safetensors

Model size

3B params

Tensor type

BF16