Nvidia Llama 3.1 Nemotron 70B Instruct HF AWQ INT4
Model Overview¶
This repository is an AWQ 4-bit quantized version of the nvidia/Llama-3.1-Nemotron-70B-Instruct-HF model, which is an NVIDIA customized version of meta-llama/Meta-Llama-3.1-70B-Instruct, originally released by Meta AI.
This model was quantized using AutoAWQ from FP16 down to INT4 using GEMM kernels, with zero-point quantization and a group size of 128.
- Model Architecture: Transformer Llama 3.1
- Model Source: ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4
- License: Llama 3.1 Community License Agreement
QPC Configurations¶
| Precision | SoCs / Tensor slicing | NSP-Cores (per SoC) | Full Batch Size | Chunking Prompt Length | Context Length (CL) | Generated URL | Download | Generation Date |
|---|---|---|---|---|---|---|---|---|
| MXFP6 | 4 | 16 | 1 | 128 | 8192 | https://dc00tk1pxen80.cloudfront.net/SDK1.20.4/ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4/qpc_16cores_128pl_8192cl_1fbs_4devices_mxfp6_mxint8.tar.gz | Download | |
| MXFP6 | 2 | 16 | 1 | 128 | 4096 | https://dc00tk1pxen80.cloudfront.net/SDK1.20.4/ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4_qpc_16cores_128pl_4096cl_1fbs_2devices_mxfp6_mxint8.tar.gz | Download | 21-Jan-2026 |
Run This Model¶
# Download QPC
mkdir -p ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4
cd ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4
wget <Download URL>
tar xzvf <downloaded filename.tar.gz>
# Run QPC
python3 -m QEfficient.cloud.execute --model_name ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4 --qpc_path <path/to/qpc> --prompt "# shortest path algorithm\n" --generation_len 128
API Endpoint¶
# Start REST endpoint with vLLM
VLLM_QAIC_MAX_CPU_THREADS=8 VLLM_QAIC_QPC_PATH=/path/to/qpc python3 -m vllm.entrypoints.openai.api_server \
--host 0.0.0.0 \
--port 8000 \
--model ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4 \
--max-model-len <Context Length> \
--max-num-seq <Full Batch Size> \
--max-seq_len-to-capture <Chunking Prompt Length> \
--device qaic \
--block-size 32