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) | QPC URL | QPC Size | QPC Download | Onnx URL | Onnx Download | Generation Date |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MXFP6 | 2 | 16 | 1 | 128 | 4096 | https://dc00tk1pxen80.cloudfront.net/SDK1.21.2/ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4/ibnzterrell_Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4_qpc_16cores_128pl_4096cl_1fbs_2devices_mxfp6_mxint8.tar.gz | 43GB | Download | https://dc00tk1pxen80.cloudfront.net/SDK1.21.2/ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4/ibnzterrell_Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4_ONNX.tar.gz | Download | 18-Mar-2026 |
Run This Model¶
Download QPCs¶
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
# 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 ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-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] comp_ctx_lengths_decode=[1024,2048,4096]"
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": "ibnzterrell/Nvidia-Llama-3.1-Nemotron-70B-Instruct-HF-AWQ-INT4",
"messages": [
{"role": "user", "content": "<PROMPT>"}
],
"max_tokens": 200
}'