Skip to content

Meta Llama 3.1 8B Instruct AWQ INT4

Model Overview

This repository is a community-driven quantized version of the original model meta-llama/Meta-Llama-3.1-8B-Instruct which is the BF16 half-precision official version released by Meta AI.

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

  • Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

This repository contains meta-llama/Meta-Llama-3.1-8B-Instruct quantized using AutoAWQ from FP16 down to INT4 using the GEMM kernels performing zero-point quantization with a group size of 128.

QPC Configurations

Precision SoCs / Tensor slicing NSP-Cores (per SoC) Full Batch Size Chunking Prompt Length Context Length (CL) QPC URL QPC Size QPC Download Onnx URL Onnx Download Generation Date
MXFP6 4 16 1 128 8192 https://dc00tk1pxen80.cloudfront.net/SDK1.21.2/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4/hugging-quants_Meta-Llama-3.1-8B-Instruct-AWQ-INT4_qpc_16cores_128pl_8192cl_1fbs_4devices_mxfp6_mxint8.tar.gz 12GB Download https://dc00tk1pxen80.cloudfront.net/SDK1.21.2/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4/hugging-quants_Meta-Llama-3.1-8B-Instruct-AWQ-INT4_ONNX.tar.gz Download 25-Mar-2026

Run This Model

Download QPCs

mkdir -p hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4
cd hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4

# Download QPC
wget <QPC_Download_URL>
tar xzvf <qpc_filename.tar.gz>

Run QPC

Replace QPC_PATH with actual extracted QPC directories.

python3 -m vllm.entrypoints.openai.api_server \
  --port <PORT> \
  --model hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4 \
  --device-group <DEVICE_IDS> \
  --max-model-len <CTX_LEN> \
  --max-seq-len-to-capture <PREFILL_SEQ_LEN> \
  --max-num-seqs <MAX_NUM_SEQS> \
  --quantization mxfp6 \
  --kv-cache-dtype mxint8 \
  --override-qaic-config "num_cores:[num_cores] qpc_path:[qpc_path] ccl_enabled:True comp_ctx_lengths_prefill=[1024,2048,4096,8192] comp_ctx_lengths_decode=[1024,2048,4096,8192]"

Run Inference

Once the server is running, send a request to the OpenAI-compatible endpoint:

curl http://localhost:<PORT>/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
    "messages": [
      {"role": "user", "content": "<PROMPT>"}
    ],
    "max_tokens": 200
  }'